This server provides an MCP interface to the Juno CLI, enabling management of Juno projects, satellites, hosting, serverless functions, configuration, changes, and documentation from any MCP-compatible client.
Identity & Auth – Check CLI/emulator versions, login (interactive or via JUNO_TOKEN), view authentication status, inspect satellite/orbiter health, and run custom JS/TS scripts in the authenticated context.
Project Setup – Scaffold new projects using Vite templates (React, Next.js, Svelte, Angular, Vue) without prompts. Initialize juno.config files in TypeScript, JavaScript, or JSON, with direct disk writing and multi-environment support. Apply configuration to satellites (storage headers, datastore rules, auth, etc.).
Hosting – Deploy, clear, and prune frontend assets. Supports batch uploads, pre-deployment clearing, post-deployment pruning, dry-run, progress/log streaming, and automatic retries.
Serverless Functions – Build, eject boilerplate, publish, and upgrade functions written in Rust, TypeScript, or JavaScript. Allows publishing from local WASM or CDN releases, with optional snapshot creation and log streaming.
Changes Workflow – List, apply, or reject submitted changes, with hash verification and optional snapshot creation.
Documentation – Fetch any of 159 official Juno documentation topics (cached) covering guides, CLI references, API docs, and framework tutorials.
Advanced Features – Progress and log streaming, automatic retries for network failures, configurable timeouts and resource limits, CLI binary caching, structured error parsing, and support for stdio or Streamable HTTP transport with automatic protocol version detection.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@junobuild-mcp-server list my satellites"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Unofficial MCP server for Juno. Not affiliated with or endorsed by the Juno team.
Manage satellites, hosting, serverless functions, changes and more through any MCP-compatible client. Includes a built-in documentation tool to access Juno's official guides and references.
19 tools across 6 domains — CLI coverage for identity, config, hosting, functions, changes, and documentation
Progress streaming — long-running operations (deploy, publish, upgrade) emit real-time progress updates via MCP notifications/progress
Log streaming — streamLogs: true mirrors raw stdout/stderr lines as MCP notifications/message events, independent of progress
Automatic retry — network-dependent operations can retry on transient failures with exponential backoff
CLI binary caching — resolves juno binary path once, eliminating npx overhead on every call
CLI version check — verifies installed @junobuild/cli meets the minimum supported version on first call
Structured error parsing — common CLI failures (auth, network, missing config) surface as actionable messages
Config file writing — juno_config_init can write config files directly to disk
Auth verification — juno_auth_status wraps juno whoami for read-only identity checks
Docs caching — documentation responses backed by an LRU cache (50 entries, 1 h TTL)
Tunable limits — character limit, default timeout, and network timeout overridable via env vars
Related MCP server: MCPJungle mcp gateway
Choose your AI coding agent below for specific setup instructions.
CLI (recommended):
claude mcp add junobuild npx -y junobuild-mcp-serverConfig file:
Scope | Location |
User |
|
Project |
|
{
"mcpServers": {
"junobuild": {
"command": "npx",
"args": ["-y", "junobuild-mcp-server"]
}
}
}CLI:
codex mcp add junobuild -- npx -y junobuild-mcp-serverConfig file:
Scope | Location |
Global |
|
Project |
|
[mcp_servers.junobuild]
command = "npx"
args = ["-y", "junobuild-mcp-server"]Config file:
Scope | Location |
User |
|
Workspace |
|
{
"mcpServers": {
"junobuild": {
"command": "npx",
"args": ["-y", "junobuild-mcp-server"]
}
}
}CLI:
droid mcp add junobuild npx -y junobuild-mcp-serverConfig file:
Scope | Location |
User |
|
Project |
|
{
"mcpServers": {
"junobuild": {
"type": "stdio",
"command": "npx",
"args": ["-y", "junobuild-mcp-server"]
}
}
}Uses a Powers system with custom configuration.
Config file:
Scope | Location |
Workspace |
|
Add the MCP server configuration to your Power's mcp.json:
{
"mcpServers": {
"junobuild": {
"command": "npx",
"args": ["-y", "junobuild-mcp-server"]
}
}
}Note: See Antigravity MCP documentation for full Power setup.
Config file:
Scope | Location |
User |
|
Project |
|
{
"mcpServers": {
"junobuild": {
"command": "npx",
"args": ["-y", "junobuild-mcp-server"]
}
}
}CLI:
amp mcp add junobuild -- npx -y junobuild-mcp-serverConfig file:
Scope | Location |
User |
|
Workspace |
|
{
"amp.mcpServers": {
"junobuild": {
"command": "npx",
"args": ["-y", "junobuild-mcp-server"]
}
}
}Note: Workspace MCP servers require approval via amp mcp approve <server-name>.
Config file:
Scope | Location |
User |
|
Workspace |
|
{
"servers": {
"junobuild": {
"type": "stdio",
"command": "npx",
"args": ["-y", "junobuild-mcp-server"]
}
}
}Config file:
Scope | Location |
User |
|
{
"mcpServers": {
"junobuild": {
"command": "npx",
"args": ["-y", "junobuild-mcp-server"]
}
}
}Config file:
Scope | Location |
User |
|
Workspace |
|
{
"mcpServers": {
"junobuild": {
"command": "npx",
"args": ["-y", "junobuild-mcp-server"]
}
}
}Config file:
Scope | Location |
User |
|
Project |
|
{
"servers": {
"junobuild": {
"command": "npx",
"args": ["-y", "junobuild-mcp-server"]
}
}
}Config file:
Scope | Location |
User |
|
{
"mcpServers": {
"junobuild": {
"command": "npx",
"args": ["-y", "junobuild-mcp-server"]
}
}
}The server builds against the 2026-07-28 protocol revision (@modelcontextprotocol/server@2) and serves both protocol eras from one toolset: 2025-era clients (e.g. Claude Desktop mid-2026) still negotiate via initialize; 2026-07-28 clients via server/discover. No flag needed — era detection is automatic per request.
Features we deliberately do not adopt (deprecated or out of scope for a CLI wrapper):
Roots and Sampling — the server is a tool runner; input is explicit tool parameters and MRTR (input_required) elicitation, not implicit sampling.
logging/setLevel (2026-era) — log gating is per-request _meta.logLevel; 2025-era sessions still get logging/setLevel via the SDK.
HTTP+SSE endpoint — the transport is Streamable HTTP with JSON responses; the deprecated SSE-across-connections mode is not served.
MRTR: juno_login asks for the credentials-encryption passphrase via input_required (the model answers the embedded form); 2025-era clients get the same flow via the SDK's legacy shim.
The server wraps @junobuild/cli, which must be installed and authenticated:
npm i -g @junobuild/cli
juno loginFor non-interactive environments (CI, headless), set the JUNO_TOKEN environment variable instead of running juno login. Tools that touch Juno state additionally accept mode and profile parameters to select an environment and identity per call.
For non-interactive environments (CI, headless), authenticate using environment variables:
export JUNO_TOKEN="your-juno-token"The server defaults to stdio. Set JUNO_MCP_TRANSPORT=http to serve over Streamable HTTP instead (default port 3000, bound to 127.0.0.1; override with JUNO_MCP_PORT):
JUNO_MCP_TRANSPORT=http JUNO_MCP_PORT=3100 node dist/main.jsThe HTTP mode is stateless and serves both protocol eras from the same toolset as stdio: 2026-07-28 clients negotiate via server/discover (modern requests must send the Mcp-Method/Mcp-Name headers), 2025-era clients via initialize. Portable to any web client or load balancer.
Smoke test with curl:
curl -X POST http://127.0.0.1:3000/mcp \
-H "Mcp-Method: server/discover" \
-H "Mcp-Name: curl" \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
-d '{"jsonrpc":"2.0","id":1,"method":"server/discover","params":{"_meta":{"io.modelcontextprotocol/protocolVersion":"2026-07-28","io.modelcontextprotocol/clientCapabilities":{},"io.modelcontextprotocol/clientInfo":{"name":"curl","version":"0"}}}}'Security: HTTP mode binds to localhost only and is unauthenticated — a local dev mode. Do not expose it to the network or pair it with a public tunnel without adding an auth layer (OAuth / reverse-proxy auth).
Override defaults to tune resource limits without rebuilding. Values must be positive integers; invalid values fall back to defaults.
Variable | Default | Description |
|
| Max characters returned in a single tool response (truncates beyond) |
|
| Default subprocess timeout in milliseconds |
|
| Timeout for network-bound operations (deploy, publish, upgrade) in ms |
|
| When |
| random | HMAC key (>=32 bytes) for MRTR |
Note: The juno_create_project tool does NOT use the interactive create-juno CLI. Instead it:
Scaffolds a Vite project (React, Next.js, Svelte, Angular, or Vue)
Creates a juno.config.ts file
This allows fully non-interactive project creation.
The juno_docs tool fetches documentation directly from the GitHub repo, with responses cached for 1 hour:
juno_docs({ topic: "build_datastore" }) → Datastore guide
juno_docs({ topic: "build_authentication" }) → Authentication overview
juno_docs({ topic: "reference_cli" }) → CLI reference
juno_docs({ topic: "guides_local_development" }) → Local development guideTopic keys use underscore naming matching folder hierarchy: build_<feature>, reference_cli_<command>, guides_<framework>. Full enumeration of all 159 topics lives in src/schemas/docs.ts (TOPICS map).
Domain | Tools |
Identity |
|
Config |
|
Hosting |
|
Functions |
|
Changes |
|
Docs |
|
Several tools support optional parameters for enhanced reliability and UX:
Parameter | Type | Tools | Description |
|
| deploy, publish, upgrade | Retry on transient network failures with exponential backoff when enabled. Attempts are set by |
|
| deploy, publish, upgrade | Maximum retry attempts when |
|
| deploy, prune | Files processed per batch (deploy default 50, prune default 100). For |
|
| deploy, publish, upgrade | Stream real-time progress updates during long-running operations (build status + upload batch progress) |
|
| deploy, publish, upgrade | Stream raw stdout/stderr lines as MCP |
|
|
| Write the config file directly to disk instead of returning text for preview |
Node.js >= 20
@junobuild/cli >= 0.15.0 — installed and authenticated (not needed for juno_version or juno_docs). Minimum version enforced on first call via checkCliVersion (src/constants.ts MIN_CLI_VERSION). Bypass with JUNO_SKIP_VERSION_CHECK=true.
Juno project with juno.config.ts/js/json (for config/hosting operations)
npm run build # Compile TypeScript to dist/
npm run dev # Watch mode (development)
npm run start # Run compiled dist/main.js
npm run clean # Remove dist/
npm test # Run unit tests
npm run test:coverage # Run tests with coverage report (v8 provider)The suite enforces the following minimum coverage (configured in vitest.config.ts):
Lines: 80%
Statements: 80%
Functions: 80%
Branches: 75%
Coverage reports are written to coverage/ (html, lcov, json, plus text summary).
npm run changeset # Create a changeset (version bump + changelog entry)
npm run version # Apply changesets → bump version
npm run release # Publish to npmThe server is a thin wrapper around the Juno CLI (@junobuild/cli): every tool
builds a command + flags, spawns the CLI via child_process, and formats the
result. Long-running tools (deploy, publish, upgrade) support three execution
strategies — simple, retry, and streaming (progress + log notifications).
Transports (chosen at startup via JUNO_MCP_TRANSPORT):
stdio (default) — one process per client over stdin/stdout
Streamable HTTP (JUNO_MCP_TRANSPORT=http, port 3000 / JUNO_MCP_PORT,
127.0.0.1) — Streamable HTTP endpoint, many clients per process
Both serve both protocol eras from the same code: 2025-era clients via
initialize, 2026-07-28 clients via server/discover. Build file is
src/main.ts (entry, transport pick); src/index.ts is a side-effect-free
buildServer() factory. Auth via juno_login (MRTR passphrase flow) uses
HMAC-signed request state.
Key design decisions are documented as ADRs in docs/adr/:
MIT
Display the current authenticated profile, access key, and links to your satellite. Use this to verify authentication before running operations that require credentials.
| Name | Required | Description | Default |
|---|---|---|---|
| mode | No | Environment mode: production, staging, or development | |
| profile | No | Profile name for multi-identity management | |
| consoleUrl | No | Specify a custom URL to access the developer Console | |
| containerUrl | No | Override a custom container URL. If omitted, the Juno CLI uses production or the local container in development mode |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, and non-destructive hints. The description adds value by specifying what is displayed (profile, access key, links) and implies a safe, informational operation. No contradictions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences, front-loaded with purpose and usage. No extraneous information, every sentence serves a clear role.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the rich annotations and complete schema, the description is adequate for understanding the tool's role. Could be improved by mentioning behavior when not authenticated, but overall sufficient.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema covers all parameters with descriptions (100% coverage). The description does not add parameter-specific context, but this is acceptable per baseline scoring. No additional guidance on how parameters affect output.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it displays authentication details (profile, access key, links), distinguishing it from sibling action tools like 'deploy' or 'apply'. However, it does not explicitly differentiate from 'juno_status', which might be a similar status tool.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description advises using this tool to verify authentication before operations requiring credentials, providing a clear usage context. It lacks explicit when-not-to-use or alternative tools, but the guidance is sufficient for the typical use case.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Apply a submitted change by its ID. Optionally create a snapshot before applying and verify the change hash for integrity.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | The ID of the change to apply | |
| hash | No | Expected hash of all included changes for verification | |
| mode | No | Environment mode: production, staging, or development | |
| profile | No | Profile name for multi-identity management | |
| snapshot | No | Create a snapshot before applying | |
| keepStaged | No | Keep proposed staged assets in memory after applying |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations indicate non-read-only, non-idempotent, non-destructive behavior with possible side effects. The description adds context about optional snapshot and hash verification, which are behavioral details beyond annotations. However, it does not elaborate on the openWorldHint side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with no filler words. It efficiently conveys the primary action and key optional features, earning every word's place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with 6 parameters (1 required) and no output schema, the description concisely covers the essential action and optional behaviors. It is adequate but could mention that the change ID must refer to a previously submitted change.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the baseline is 3. The description only mentions 'its ID' and optional snapshot/hash, which repeats schema info without adding new meaning beyond the structured fields.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Apply a submitted change by its ID') and distinguishes from siblings like juno_changes_list (list) and juno_changes_reject (reject). It also highlights optional behaviors (snapshot, hash verification), making the specific resource and verb unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The context for use is clear—apply a submitted change—but there is no explicit when-not-to-use or comparison to alternative tools. The description implies usage for applying changes but lacks exclusions or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List all submitted or applied changes to your module. By default shows only submitted (pending) changes. Use --all for full history and --every to include all statuses.
| Name | Required | Description | Default |
|---|---|---|---|
| all | No | Search through all changes, not just the 100 most recent | |
| mode | No | Environment mode: production, staging, or development | |
| every | No | Include changes of any status (default is only submitted ones) | |
| profile | No | Profile name for multi-identity management |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description adds value by explaining the default filtering and scope, but does not cover return format or pagination limits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loading the main purpose, with no redundant information. Every sentence contributes value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description covers the main behavior and key flags, but lacks details on pagination limits (implied by 'all' schema), response format, and explanation of 'mode' and 'profile' parameters.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the baseline is 3. The description reiterates the meaning of 'all' and 'every' and notes the default, providing marginal additional context.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'List' and the resource 'changes to your module', distinguishing it from sibling tools like juno_changes_apply and juno_changes_reject which perform mutations.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explains the default behavior (only submitted changes) and when to use the --all and --every flags. However, it does not explicitly compare to alternatives or state when not to use this tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Reject a submitted change by its ID. This prevents the change from being applied. Optionally verify the change hash for integrity.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | The ID of the change to reject | |
| hash | No | Expected hash of all included changes for verification | |
| mode | No | Environment mode: production, staging, or development | |
| profile | No | Profile name for multi-identity management | |
| keepStaged | No | Keep proposed staged assets in memory after rejecting |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate destructiveHint=true and readOnlyHint=false. The description adds value by explaining that rejection prevents application and optionally verifies hash integrity. No contradictions with annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, front-loaded with the core action, and no extraneous information. Highly concise and efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a rejection tool with destructive side effects, the description explains the primary behavior. Lacks details on reversibility or prerequisites, but is sufficient given the tool's simplicity and the presence of annotations.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so baseline is 3. The description mentions optional hash verification, adding context beyond the schema, but does not elaborate on other parameters. Overall, minimal added value over schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Reject a submitted change by its ID') and the effect ('prevents the change from being applied'). It distinguishes from sibling tools like juno_changes_apply and juno_changes_list by specifying a rejection action.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies when to use the tool (to prevent a change from being applied), but does not explicitly contrast with alternatives or provide exclusion criteria. It is clear but lacks explicit guidance compared to siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Apply the current juno.config file to your satellite. This is required after modifying settings like storage headers, datastore rules, authentication config, or collection definitions.
| Name | Required | Description | Default |
|---|---|---|---|
| mode | No | Environment mode: production, staging, or development | |
| force | No | Overwrite configuration without checks | |
| profile | No | Profile name for multi-identity management | |
| consoleUrl | No | Specify a custom URL to access the developer Console | |
| containerUrl | No | Override a custom container URL. If omitted, the Juno CLI uses production or the local container in development mode |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations indicate this is not read-only and not destructive. Description adds that it applies the config but lacks details on side effects (e.g., service restarts) or prerequisites (e.g., valid config file). No contradiction with annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, front-loaded with the main action. No redundant information; every word serves a purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Completes the purpose and usage well, but lacks mention of return values or error handling. Since no output schema, a brief note on success/failure would improve completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so all parameters are already described. The description adds no parameter-specific details beyond the schema examples of settings. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states the action (apply config) and resource (satellite), with specific examples of settings that require this step. Differentiates from sibling tools like juno_config_init.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly says 'required after modifying settings' and lists examples, providing clear context on when to use. Does not mention alternatives or when not to use, but the context is strong.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Generate a juno.config file (TypeScript, JavaScript, or JSON). By default returns config content for preview. Set writeFile to true to write the file directly to disk. Then run juno_config_apply to push the config to your satellite.
| Name | Required | Description | Default |
|---|---|---|---|
| path | No | Custom file path for the config (defaults to juno.config.ts/js/json in project root) | |
| format | No | Config file format | typescript |
| source | No | Build output directory (e.g. dist, build, out) | dist |
| multiEnv | No | Generate multi-environment config with staging and production satellite IDs | |
| orbiterId | No | Optional Orbiter ID for analytics | |
| writeFile | No | Write the config file directly to disk instead of returning content for preview | |
| satelliteId | No | Satellite ID for production environment. Use a real ID or leave the placeholder. | aaaaa-bbbbb-ccccc-ddddd-cai |
| stagingSatelliteId | No | Staging satellite ID (required if multiEnv is true) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses default behavior (preview) and writeFile option. Aligns with annotations (idempotent, non-destructive). No contradictions; adds meaningful context beyond annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, front-loaded with purpose and followed by actionable workflow. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 8 parameters and no output schema, the description sufficiently explains purpose, options, and follow-up tool. Could mention return value format, but adequate.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema covers all 8 parameters (100%). Description adds workflow context (preview/write, multi-env) beyond schema definitions, justifying an above-baseline score.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool generates a juno.config file in TypeScript, JavaScript, or JSON, and differentiates from sibling juno_config_apply by noting it's for generation before pushing.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Indicates when to use (generate config) and mentions the next step (juno_config_apply). Provides context on preview vs writeFile, but lacks explicit when-not-to-use or alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Scaffold a new Juno project. Uses Vite to create the frontend, then adds Juno SDK and config. Does NOT use the interactive create-juno CLI.
| Name | Required | Description | Default |
|---|---|---|---|
| template | No | Template key to use (e.g. react-ts-starter, nextjs-starter, sveltekit-starter). Defaults to react-ts-starter. | |
| directory | Yes | Directory name for the new project | |
| packageManager | No | Package manager to use (npm, yarn, pnpm) | npm |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations provide no destructive hint, and description adds key behavior: non-interactive (avoids create-juno CLI) and uses Vite. This goes beyond annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences with no wasted words; front-loaded purpose and critical nuance about non-interactivity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Fairly complete for a scaffolding tool with no output schema. Could mention that it creates files in a new directory, but not essential.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Description does not elaborate on parameters beyond what schema provides. With 100% schema coverage, baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it scaffolds a new Juno project using Vite and adding Juno SDK/config, distinguishing it from sibling tools like juno_auth_status or juno_config_apply.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies when to use (creating a new project) but lacks explicit when-not or alternatives. However, no sibling tool overlaps, so context is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Fetch Juno documentation from GitHub repo. Full docs: https://github.com/junobuild/docs/tree/main/docs. Topics use underscore naming matching folder hierarchy (e.g. build_authentication, reference_cli_functions_build).
| Name | Required | Description | Default |
|---|---|---|---|
| topic | Yes | Documentation topic to retrieve. Full Juno docs from GitHub repo: https://github.com/junobuild/docs/tree/main/docs |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is clear. The description adds the source (GitHub repo) and naming convention, but does not detail response format or error behavior. Value added but not rich.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three concise sentences: purpose, source URL, naming convention. Front-loaded with critical info, no wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple one-parameter tool with strong annotations, the description covers source, naming, and reference. It lacks response format (e.g., raw markdown or HTML), but is adequate for a documentation fetch tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with enum list. Description adds meaning beyond schema by explaining the underscore naming pattern and folder hierarchy relationship (e.g., build_authentication), which helps agents understand topic structure.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Fetch Juno documentation from GitHub repo' with a specific verb and resource. It distinguishes from sibling tools which are action-oriented (e.g., deploy, build), as this is the only documentation retrieval tool.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear context: the documentation source URL and the underscore naming convention that mirrors folder hierarchy. While it doesn't explicitly state when-not to use or offer alternatives, the context is sufficient for an agent to understand usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Build your serverless functions. Supports Rust, TypeScript, and JavaScript. The CLI auto-detects the language if not specified.
| Name | Required | Description | Default |
|---|---|---|---|
| lang | No | Language for building serverless functions | |
| watch | No | Rebuild your functions automatically when source files change | |
| cargoPath | No | Path to the Rust manifest (Cargo.toml) | |
| sourcePath | No | Path to the TypeScript or JavaScript entry file |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations are all false, so no contradiction. The description adds auto-detection behavior but does not disclose potential side effects (e.g., overwriting old builds) or other traits like rate limits. Basic but not rich.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences with no wasted words. The main action is front-loaded, and the language support list is clear. Perfect conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and 4 parameters, the description is somewhat complete but lacks information about build outputs, prerequisites (e.g., project must be initialized), or error scenarios. Adequate but not comprehensive.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, and the description adds the key detail that language auto-detection occurs if unspecified. This provides meaningful context beyond the schema descriptions, though it doesn't elaborate on each parameter's syntax.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it builds serverless functions and lists supported languages. It distinguishes from siblings like publish and eject, but does not explicitly differentiate them, so slightly below perfect.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It implies usage before publishing but does not provide explicit guidance on when to use or alternatives. No exclusions or context for language selection is given, making it adequate but not helpful.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Generate the required files to begin developing serverless functions in your project. Scaffolds boilerplate for Rust, TypeScript, or JavaScript functions. Alias: juno functions init.
| Name | Required | Description | Default |
|---|---|---|---|
| lang | No | Language for scaffolding serverless functions |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare idempotentHint=true and destructiveHint=false. The description adds context about scaffolding boilerplate but does not disclose side effects like file overwriting or location. Description is consistent with annotations but adds limited behavioral depth.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences with no wasted words, front-loaded with action and resource. Efficient and clear.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple scaffold tool with one parameter and good annotations, the description covers core purpose and language options. It lacks detail on output location or overwrite behavior, but annotations fill some gaps. Reasonably complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% and includes enum for lang. The description lists the same language options ('Rust, TypeScript, or JavaScript') reinforcing but not adding new meaning beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'generate' and resource 'required files for serverless functions', with language options. It distinguishes from siblings by mentioning it's an initialization step (alias: init). However, it does not explicitly contrast with other juno_functions tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage as a first step ('to begin developing'), but provides no explicit when-to-use vs alternatives, no prerequisites, and no when-not-to-use. The alias helps, but guidance is minimal.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Publish a new version of your serverless functions to the satellite. Optionally submit as a pending change without applying, or provide a custom WASM file path.
| Name | Required | Description | Default |
|---|---|---|---|
| src | No | Path to a specific local gzipped WASM file to publish | |
| mode | No | Environment mode: production, staging, or development | |
| retry | No | Automatically retry on transient network failures (up to 3 attempts with exponential backoff) | |
| noApply | No | Submit the release as a change but do not apply it yet | |
| profile | No | Profile name for multi-identity management | |
| progress | No | Stream progress updates during publish (shows build status and upload batch progress) | |
| consoleUrl | No | Specify a custom URL to access the developer Console | |
| keepStaged | No | Keep proposed staged assets in memory after applying | |
| streamLogs | No | Stream raw stdout/stderr log lines as MCP notifications/message events. Independent from progress. | |
| containerUrl | No | Override a custom container URL. If omitted, the Juno CLI uses production or the local container in development mode |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate write operation (readOnlyHint=false) and lack of idempotency. The description adds no behavioral context beyond parameter options, failing to disclose side effects, authentication needs, or state changes beyond basic function.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single sentence that efficiently conveys the main action and two optional features. No unnecessary words or repetition.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description covers the primary action but omits return value or post-publish behavior. With no output schema, some description of expected output or next steps would improve completeness. Adequate for a tool with detailed schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with clear parameter descriptions. The description hints at two key options (noApply, src) but adds no meaning beyond what the schema provides. Baseline score of 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly identifies the tool as publishing new versions of serverless functions to a satellite, with optional behaviors (pending change, custom WASM path). It distinguishes from siblings like juno_functions_build (builds) and juno_functions_upgrade (upgrades).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for publishing functions but does not explicitly state when to use or avoid this tool versus alternatives. No exclusions or preferred contexts are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Upgrade your satellite's serverless functions. Can use a local WASM file, select from CDN releases, or use the default local build output. Optionally create a snapshot before upgrading.
| Name | Required | Description | Default |
|---|---|---|---|
| cdn | No | Select a previously published WASM file from the CDN (interactive) | |
| src | No | Path to a specific local gzipped WASM file | |
| mode | No | Environment mode: production, staging, or development | |
| reset | No | Reset to the initial state | |
| retry | No | Automatically retry on transient network failures (up to 3 attempts with exponential backoff) | |
| cdnPath | No | Use a specific published WASM file from the CDN | |
| profile | No | Profile name for multi-identity management | |
| progress | No | Stream progress updates during upgrade (shows build status and upload batch progress) | |
| consoleUrl | No | Specify a custom URL to access the developer Console | |
| noSnapshot | No | Skip creating a snapshot before upgrading | |
| streamLogs | No | Stream raw stdout/stderr log lines as MCP notifications/message events. Independent from progress. | |
| clearChunks | No | Clear previously uploaded WASM chunks | |
| containerUrl | No | Override a custom container URL. If omitted, the Juno CLI uses production or the local container in development mode |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations indicate a write operation (readOnlyHint=false) and non-idempotent. The description adds that a snapshot can be optionally created, implying reversibility. However, it does not disclose other behavioral traits like potential downtime, error states, or what happens to old functions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is three sentences, each serving a distinct purpose: stating the action, listing methods, and noting an optional feature. It is front-loaded with the purpose and wastes no words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description covers the core action and key options, but given the tool has 13 parameters and no output schema, it lacks detail on what happens post-upgrade, error handling, or interaction with other tools. Some behavioral context is missing.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so all 13 parameters have individual descriptions. The tool description adds summarized context (three WASM sourcing methods) but does not address the majority of parameters (e.g., mode, retry, progress). The description adds marginal value beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool upgrades satellite serverless functions, lists three specific methods (local WASM, CDN releases, default build output), and mentions optional snapshot creation. It distinguishes from sibling tools like build or publish by focusing on the upgrade action.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage through the listed methods but does not explicitly state when to use this tool versus alternatives like juno_functions_build or juno_functions_publish. No prerequisites or exclusion criteria are provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Remove frontend files (JS, HTML, CSS, etc.) from your satellite. This does NOT remove user-uploaded files from custom collections — only the deployed app assets.
| Name | Required | Description | Default |
|---|---|---|---|
| mode | No | Environment mode: production, staging, or development | |
| profile | No | Profile name for multi-identity management | |
| fullPath | No | Clear a particular file by its path | |
| consoleUrl | No | Specify a custom URL to access the developer Console | |
| containerUrl | No | Override a custom container URL. If omitted, the Juno CLI uses production or the local container in development mode |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark the tool as destructive and not read-only. The description adds valuable behavioral context by specifying that user-uploaded files from custom collections are not affected, which is beyond what annotations provide. No contradiction with annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise with two sentences. It front-loads the key action and scope, and every word adds value. No fluff or redundant information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's destructive nature, optional parameters, and lack of output schema, the description provides essential context about what is removed and what is preserved. However, it does not explain behavior across different environments (production, staging, development) or the effect of specifying 'fullPath', but these are somewhat covered by the schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the baseline is 3. The description does not add any additional meaning or guidance for the parameters (mode, profile, fullPath, consoleUrl, containerUrl) beyond what the schema already provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Remove') and the specific resource ('frontend files (JS, HTML, CSS, etc.) from your satellite'). It distinguishes the tool from siblings like 'juno_hosting_deploy' and 'juno_hosting_prune' by specifying what is removed and what is not (user-uploaded files).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implicitly indicates usage by stating it removes only deployed app assets and not user-uploaded files, but it lacks explicit guidance on when to use this tool versus alternatives like 'juno_hosting_prune' or other sibling tools. No 'when-not' or alternative recommendations are provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Deploy your app's frontend files to your satellite. Reads from the source directory defined in juno.config and uploads all assets. Supports batch parallelism, clearing before deploy, and pruning stale files after.
| Name | Required | Description | Default |
|---|---|---|---|
| mode | No | Environment mode: production, staging, or development | |
| batch | No | Number of files to upload in parallel per batch (1-200) | |
| clear | No | Clear existing app files before deployment | |
| prune | No | Prune stale app files after successful deployment | |
| retry | No | Automatically retry on transient network failures (up to 3 attempts with exponential backoff) | |
| config | No | Apply configuration after deployment succeeds | |
| noApply | No | Submit deployment as a change but do not apply it yet | |
| profile | No | Profile name for multi-identity management | |
| progress | No | Stream progress updates during deployment (shows build status and upload batch progress) | |
| immediate | No | Deploy files instantly bypassing the change workflow | |
| consoleUrl | No | Specify a custom URL to access the developer Console | |
| keepStaged | No | Keep proposed staged assets in memory after applying | |
| streamLogs | No | Stream raw stdout/stderr log lines as MCP notifications/message events. Independent from progress. | |
| containerUrl | No | Override a custom container URL. If omitted, the Juno CLI uses production or the local container in development mode |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate non-readonly and non-idempotent behavior. The description adds useful context about source directory, batch parallelism, and options for clearing/pruning. However, it does not disclose potential consequences like downtime or overwriting, which would be expected for a deployment tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences: first sentence states the core purpose, second lists key features. No wasted words, appropriately front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description lacks information about return values (no output schema), prerequisites, and post-deployment behavior. For a tool with 14 parameters, it is somewhat terse but covers the primary action adequately.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 100% schema description coverage, the schema already documents all parameters adequately. The description briefly echoes batch, clear, and prune but adds no new semantic meaning. Baseline of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb (Deploy), resource (app's frontend files to your satellite), and scope (reads from source directory). It distinguishes from sibling tools like juno_hosting_clear and juno_hosting_prune by mentioning them as sub-actions.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description does not provide explicit guidance on when to use this tool versus alternatives. It lists supported features but fails to differentiate from siblings like juno_functions_publish or juno_config_apply, nor does it state when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Remove stale frontend files from your satellite that are no longer in your build output. Use --dry-run to preview which files would be deleted without actually deleting them.
| Name | Required | Description | Default |
|---|---|---|---|
| mode | No | Environment mode: production, staging, or development | |
| batch | No | Number of files to prune in parallel per batch (1-200) | |
| dryRun | No | List stale files without actually deleting them | |
| profile | No | Profile name for multi-identity management | |
| consoleUrl | No | Specify a custom URL to access the developer Console | |
| containerUrl | No | Override a custom container URL. If omitted, the Juno CLI uses production or the local container in development mode |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate destructiveHint=true and readOnlyHint=false. The description adds the dry-run safety feature but does not disclose batch processing behavior, idempotency issues, or that it runs per environment. It provides some added value but remains incomplete.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences, front-loaded with purpose, no unnecessary words. Every sentence earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description lacks context for a destructive tool: no mention of prerequisites (e.g., after deploy), no description of outcomes, no guidance on when to use with modes or batch parameters. Given no output schema, more detail is needed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the description's mention of --dry-run does not add new meaning beyond what the schema already provides. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Remove' and resource 'stale frontend files' with context 'from your satellite' and condition 'no longer in build output'. It is specific but does not explicitly distinguish from sibling tools like juno_hosting_clear.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description mentions using --dry-run for preview but provides no guidance on when to use this tool versus alternatives (e.g., juno_hosting_deploy or juno_hosting_clear), nor any scenarios where it should not be used.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Run a custom JavaScript or TypeScript script in the CLI context. The script has access to the authenticated Juno environment.
| Name | Required | Description | Default |
|---|---|---|---|
| src | Yes | Path to your JavaScript or TypeScript script | |
| mode | No | Environment mode: production, staging, or development | |
| profile | No | Profile name for multi-identity management | |
| containerUrl | No | Override a custom container URL. If omitted, the Juno CLI uses production or the local container in development mode |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations indicate readOnlyHint=false (potential writes), openWorldHint=true (external calls), and idempotentHint=false. The description does not disclose side effects, such as whether the script can modify the Juno environment, produce persistent changes, or require specific permissions. This is insufficient for a tool that executes arbitrary code.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, which is concise but could be better structured. It conveys core purpose without wasted words, though it could benefit from a brief follow-up on usage scope.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of executing arbitrary scripts and the absence of an output schema, the description lacks details on execution environment, expected outputs, error handling, or when to use this tool over sibling tools like juno_functions_build or juno_hosting_deploy. More context is needed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, providing basic descriptions for each parameter. The description adds no additional meaning beyond the schema. Baseline score of 3 is appropriate as the schema already explains parameters like src, mode, profile, and containerUrl.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool runs custom JS/TS scripts in the CLI context with access to the authenticated Juno environment. This distinguishes it from sibling tools which are specific operations (e.g., deploy, build). However, it could be more specific about what 'CLI context' entails.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool vs alternatives. The description lacks context on scenarios where running a custom script is preferred over using specific Juno commands like juno_hosting_deploy or juno_config_apply.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Check the status of your modules (satellites, orbiters). Shows health, deployment status, and more.
| Name | Required | Description | Default |
|---|---|---|---|
| mode | No | Environment mode: production, staging, or development | |
| profile | No | Profile name for multi-identity management | |
| consoleUrl | No | Specify a custom URL to access the developer Console | |
| containerUrl | No | Override a custom container URL. If omitted, the Juno CLI uses production or the local container in development mode |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already provide readOnlyHint, openWorldHint, idempotentHint, and destructiveHint, so the description does not need to repeat them. It adds value by mentioning what is shown (health, deployment status) and hints at additional unspecified information ('and more'), which is acceptable for a status tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, well front-loaded, and every word provides value. No wasted language, making it easy for an agent to parse quickly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (4 optional parameters, no required, no output schema), the description is mostly complete. It could benefit from specifying what 'more' entails, but the annotations fill the gaps in behavioral context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, meaning each parameter is already documented in the input schema. The description does not add any parameter-specific details, so the baseline of 3 is appropriate as the schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: to check the status of modules (satellites, orbiters) and shows health and deployment status. This verb+resource combination is specific and distinguishes it from sibling tools like juno_auth_status or juno_changes_apply.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies when to use it (to check module status), but it does not provide explicit guidance on when not to use it or mention alternatives. There is no comparison to siblings, leaving the agent to infer usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Show the current versions of the Juno CLI and emulator (if running). Use --version flag.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and idempotentHint=true, indicating safe read operations. The description adds context that the emulator version is shown only if running, which is useful behavioral information beyond the annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences long, concise, and front-loaded with the core action. Every word serves a purpose, with no redundancy or unnecessary detail.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description lacks specification of the output format or what exactly is returned (e.g., version numbers, strings). Given no output schema, the description should clarify the return value to fully inform the agent. It is adequate but not complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With zero parameters and 100% schema coverage, the description does not need to add parameter semantics. The baseline of 4 is appropriate as the schema already fully documents the parameter set.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description explicitly states the tool shows current versions of Juno CLI and emulator (if running), providing a specific verb and resource. It clearly distinguishes from sibling tools like juno_auth_status or juno_changes_apply which serve different purposes.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for checking versions and mentions the --version flag, but it does not explicitly state when to use this tool versus alternatives or provide exclusion criteria. Usage guidance is implied but not fully explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v1.5.0juno_auth_statusjuno_changes_applyjuno_changes_listjuno_changes_rejectjuno_config_applyjuno_config_initjuno_create_projectjuno_docsjuno_functions_buildjuno_functions_ejectjuno_functions_publishjuno_functions_upgradejuno_hosting_clearjuno_hosting_deployjuno_hosting_prunejuno_runjuno_statusjuno_versionEach tool targets a distinct resource and action. The domain prefixes (auth, changes, config, etc.) clearly separate concerns, and within each domain, tools like apply, list, reject are unambiguous.
Tools follow a consistent juno_<domain>_<action> pattern, with occasional noun-only names (juno_docs, juno_status) and both singular and plural forms. Minor variations exist but the pattern is clear.
18 tools cover the main aspects of Juno satellite management (auth, changes, config, functions, hosting, etc.) without being overwhelming. The count feels well-scoped for the domain.
The tool set covers core workflows: authentication, config management, changes (apply, list, reject), functions lifecycle, hosting operations, and status checks. Missing are direct user/datastore CRUD or config viewing, but these are out of scope for a CLI-focused MCP.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Official Sevalla MCP — full PaaS API access through just 2 tools.
Build, deploy, and host full-stack web apps from any MCP client. DB, auth, storage, cron included.
Governed MCP gateway: one endpoint for your tools, with credential custody and audit log.
List, read, edit, and deploy your GenMB AI-generated apps from any MCP client.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/nami2111/junobuild-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
