The CompText MCP Server provides deterministic, read-only workspace inspection and context packaging tools for a Rust/CompText project environment, without network access or external dependencies.
comptext_status – Retrieve the current status of CompText, Rust, Cargo, Git, and the overall workspace.
comptext_pack_context – Generate a deterministic context pack with stable file ordering and SHA-256 hashes (configurable byte limit, default 250,000 bytes).
comptext_rust_audit – Run safe, read-only Rust checks including cargo check, optional Clippy linting, and test compilation (without executing tests).
comptext_replay_digest – Produce a deterministic replay/evidence digest of the current workspace state (configurable byte limit, default 250,000 bytes).
comptext_contract_check – Verify local safety contracts for OpenCode usage.
comptext_github_pack – Prepare a local GitHub summary pack without making any network calls.
comptext_hf_export_pack – Generate Hugging Face Space/Card export text locally, without any upload or token usage.
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., "@CompText MCP pack context for current project"
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.
comptext-mcp is the planned MCP contract layer for exposing deterministic
local ctxt --json results to MCP clients.
Phase 0 is documentation-only. This repository baseline does not implement an MCP server, package runtime, provider integration, token passthrough, proposal application, network access, external-agent invocation, or general shell access. Pre-existing runtime and package files may be present in the repository, but they are outside Phase 0 scope and are not treated as release-ready behavior by this documentation baseline.
Core principle:
Models are providers. Context is the product.
ctxt is the deterministic source of truth.
ctxt owns behavior, schemas, validation, and deterministic context.
comptext-mcp must not invent behavior.
comptext-mcp is a future adapter only.
Future MCP tools must map one-to-one to stable local ctxt --json commands.
Runtime artifacts and proposal artifacts are untrusted evidence, not workspace truth.
Related MCP server: Context Snipe
Phase 0 creates the documentation and contract baseline only:
PROJEKT.md
README.md
.gitignore
SECURITY.md
docs/ARCHITECTURE.md
docs/CONTRACTS.md
docs/ROADMAP.md
No runtime code, package scaffolding, server implementation, generated reports, hooks, plugins, dependencies, provider calls, proposal application, or general shell access are part of Phase 0.
@github, @codex-security, and @openai-developers may be used only as
review and context tools for Phase 0 documentation. They do not grant
permission to create runtime code, call providers, enable network behavior,
create server implementation, add token passthrough, create hooks or plugins,
invoke external agents, apply proposals, or write git history.
Subagents, if used, are limited to deterministic review and planning over Phase 0 docs, security boundaries, tool mappings, and consistency.
Future MCP tools may only wrap these stable local commands:
ctxt --json self report
ctxt --json schema
ctxt --json capabilities
ctxt --json proposals list
ctxt --json proposals inspect latest --max-bytes 12000
ctxt --json proposals inspect --id latest --max-bytes 12000
ctxt --json proposals validate latest
ctxt --json proposals validate --id latest
ctxt --json validate --run
ctxt --json agent discover
ctxt --json runs list
ctxt --json runs read latest --max-bytes 12000Unsupported ctxt commands are not part of the Phase 0 MCP contract.
Check local safety contracts for OpenCode usage.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It only says 'check', implying a read-only operation, but does not specify whether it has side effects, requires authentication, or has rate limits. Minimal transparency.
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 that is front-loaded and contains no fluff. It is appropriately concise for a zero-parameter tool, though slightly more context could be added without bloat.
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 parameters and an existing output schema, the description is minimally adequate. It lacks details on what the check returns or what 'local safety contracts' are, but the output schema likely provides the structure.
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?
No parameters exist, so schema coverage is 100%. The description adds no extra meaning beyond the schema, resulting in a baseline score of 3.
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 checks local safety contracts for OpenCode usage, which is a specific verb-resource pair. It distinguishes from sibling tools like comptext_status that likely provide general status rather than contract checking.
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 guidance provided on when to use this tool versus alternatives. There is no mention of typical scenarios, prerequisites, or context for using the check.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Prepare a local GitHub summary pack without network calls.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description provides one behavioral trait (no network calls). It does not disclose whether the tool is read-only, destructive, or what side effects occur. This is adequate but not comprehensive.
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 unnecessary words. It is front-loaded 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 tool with no parameters and an output schema (not provided), the description gives essential information (action, outcome, key constraint). However, it could clarify what a 'summary pack' contains relative to sibling tools like comptext_pack_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?
There are zero parameters and schema coverage is 100%. The description adds no parameter-level detail, which is acceptable. Baseline score of 4 for no parameters.
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 (prepare) and resource (local GitHub summary pack) and adds a key constraint (without network calls). It is distinguishable from sibling tools based on the name and context, but lacks explicit definition of what a 'GitHub summary pack' 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 guidance on when to use this tool versus alternatives. The phrase 'without network calls' implies an offline preference but does not specify scenarios or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Return Hugging Face Space/Card export text without upload or token usage.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided. The description mentions 'without upload or token usage,' suggesting read-only behavior and low risk, but it does not disclose other behavioral traits such as prerequisites, rate limits, or error conditions.
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 wasted words. It is front-loaded and efficiently conveys the essential 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?
Given that the tool has no parameters and a straightforward purpose, the description is mostly complete. An output schema exists, so return value details are not needed. However, a bit more context on what 'Hugging Face Space/Card export text' includes 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?
The tool has no parameters, and schema coverage is 100% (no parameters to describe). According to the guidelines, the baseline score for 0 parameters is 4. The description does not need to add parameter semantics.
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 that the tool returns Hugging Face Space/Card export text without requiring upload or token usage. This is a specific verb and resource, and sibling tools are unrelated, so there is no confusion.
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 this tool (when no upload/token is desired) but does not explicitly state when not to use it or compare it with alternatives. No explicit usage guidelines are provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Create a deterministic context pack with stable file order and sha256 hashes.
| Name | Required | Description | Default |
|---|---|---|---|
| max_bytes | No |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It mentions deterministic behavior and sha256 hashes, but fails to disclose whether the tool is idempotent, has side effects (e.g., file creation), or requires specific permissions. Mutation intent is implied but not explicitly clarified.
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 fluff, but it sacrifices information for brevity. Parameter details are missing, making it less useful despite being concise.
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?
Despite having only one parameter and an output schema (unknown content), the description fails to explain how 'max_bytes' affects the context pack (e.g., truncation behavior). For a simple tool, this gap is significant.
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?
The only parameter 'max_bytes' (optional, default 250KB) is entirely undocumented in the description. Schema description coverage is 0%, so the description provides no meaning beyond the schema itself. The parameter's purpose, effect, and acceptable values are absent.
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 creates a 'deterministic context pack' with 'stable file order and sha256 hashes,' distinguishing it from sibling tools like 'comptext_contract_check' or 'comptext_github_pack'. However, the term 'context pack' may be domain-specific and could be clearer.
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 guidance on when to use this tool vs. alternatives (e.g., when a non-deterministic pack is acceptable). No mention of prerequisites, limitations, or 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.
Create a deterministic replay/evidence digest for the current workspace.
| Name | Required | Description | Default |
|---|---|---|---|
| max_bytes | No |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden but only mentions 'deterministic replay/evidence digest', without explaining what this means, whether the tool modifies state, requires auth, or has side effects. The term 'deterministic' hints at reproducibility but is not elaborated.
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 omits critical details. While it is front-loaded, it sacrifices informativeness for brevity. 3 reflects adequacy with clear gaps.
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?
Although the tool has an output schema (not shown), the description does not clarify return values. For a simple tool, more context is needed about what the digest contains and how 'deterministic' applies. Current text is insufficient for confident invocation.
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?
The schema has 0% description coverage for the single parameter 'max_bytes'. The description does not explain its purpose or effect, leaving the agent to guess. Baseline for low coverage requires compensation, but none is provided.
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 ('Create') and resource ('deterministic replay/evidence digest') for the current workspace. However, it does not differentiate from sibling tools like comptext_pack_context or comptext_status, which could also relate to workspace contexts.
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 guidance is provided on when to use this tool versus siblings, nor any prerequisites or exclusions. The description lacks context about typical use cases or when alternatives are better.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Run safe read-only Rust checks.
| Name | Required | Description | Default |
|---|---|---|---|
| check | No | ||
| clippy | No | ||
| tests_no_run | No |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description explicitly states 'safe read-only', disclosing non-destructiveness. However, no annotations are present, so the description carries the burden. It does not detail what checks are performed, error behavior, or prerequisites, leaving gaps in transparency.
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 wasted words, but it is too brief to be fully useful. It sacrifices informativeness for brevity, resulting in a structure that could be expanded with key details while remaining concise.
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 presence of three parameters and an output schema, the description is insufficient. It does not explain the tool's role within the sibling context, the meaning of parameters, or expected outputs. The tool's complexity demands more context for effective agent usage.
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 0%, meaning the schema itself provides no descriptions for the three boolean parameters (check, clippy, tests_no_run). The tool description fails to explain any parameter semantics, leaving the agent without guidance on how to use them.
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?
Description states 'Run safe read-only Rust checks', which clearly identifies a specific verb (run), resource (Rust checks), and a key trait (read-only). This distinguishes it from sibling tools that focus on contracts, packaging, etc.
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 guidance is provided on when to use this tool versus alternatives like comptext_contract_check or comptext_github_pack. The description implies usage for Rust auditing but lacks explicit context or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Return CompText, Rust, Cargo, Git, and workspace status.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description bears full burden for disclosing behavior. It only says 'Return ... status' without indicating whether it is a read-only operation, if it fetches data, or any side effects. This is insufficient for a tool that likely performs checks.
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?
Single sentence, no wasted words, directly states what the tool returns. Appropriate length and structure for a simple status tool.
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 parameters and existence of output schema, description lists components returned but lacks behavioral context (e.g., is it a local check, network-dependent?). Adequate but could be more complete by mentioning read-only nature or performance characteristics.
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?
No parameters exist in schema (0 params), and schema coverage is 100% (empty). Baseline for 0 params is 4, and description adds nothing needed about parameters.
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?
Description clearly states it returns status of multiple components (CompText, Rust, Cargo, Git, workspace), which distinguishes it from sibling tools that focus on contract checks, packing, audits, etc. However, it could be more specific about what 'status' entails (e.g., version info, health indicators).
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 guidance on when to use this tool versus alternatives, or any prerequisites. The description implies it's for checking status but provides no context on scenarios or exclusions.
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.
v0.1.0comptext_contract_checkcomptext_github_packcomptext_hf_export_packcomptext_pack_contextcomptext_replay_digestcomptext_rust_auditcomptext_statusEach tool has a clearly distinct purpose: contract checking, GitHub packaging, Hugging Face export, context packing, replay digest, Rust audit, and status. There is no overlap or ambiguity.
All tools follow a consistent 'comptext_' prefix followed by descriptive snake_case names (e.g., comptext_contract_check, comptext_status). The pattern is uniform and predictable.
With 7 tools, the count is well within the ideal range (3-15). Each tool serves a clear function without excess or deficiency for the server's apparent scope.
The tools cover core workflows: contract checks, exports, context packing, digests, audits, and status. Minor gaps might exist (e.g., no tool for clearing or resetting state), but the set is largely complete for typical usage.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Turn a GitHub repo or docs site into agent-ready context: pack it or search it, over MCP.
A paid remote MCP for OpenAI Codex context compressor, built to return verdicts, receipts, usage log
Free OpenAI-compatible inference with signed provenance receipts and 3 focused MCP tools.
Production-grade cryptography toolkit with 31 MCP tools for classical, PQC, and KMS workflows.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/ProfRandom92/comptext-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server