This server exposes your codebase for AI agents to analyze, navigate, and understand code repositories with compressed, token-efficient responses.
index_repo: Walk a Python/JavaScript/TypeScript repo (up to 3 levels deep) and return a full structural index of every function, class, import, and dependency — skipping noise like __pycache__, .git, venv, and node_modules.
get_compressed: Compress a single source file (Python or JS/TS) by stripping function bodies and retaining only signatures and dependency contracts, returning token stats (before, after, and reduction percentage).
expand: Retrieve the full verbatim source of specific functions or classes from a .py file, along with their compressed dependency context.
blast_radius: Perform reverse-call-graph impact analysis on a Python function to find every function transitively affected if that function changes — returns direct callers, all impacted functions, a count, and a risk level (LOW / MEDIUM / HIGH).
security_surface: Scan a Python repo using pure AST analysis to identify dangerous calls (HIGH risk: subprocess, eval, exec, pickle, etc.; MEDIUM risk: requests, httpx, socket, write-mode open, etc.) and detect potential hardcoded secrets (API keys, tokens, passwords), returning a categorized risk report.
Provides compressed MCP proxy access to GitHub tools, reducing token usage for operations like repository management, issues, and pull requests.
Provides compressed MCP proxy access to Gmail tools, reducing token usage for email operations.
Provides compressed MCP proxy access to Google Calendar tools, reducing token usage for calendar management.
Provides compressed MCP proxy access to Slack tools, reducing token usage for messaging and channel management.
Cuts up to 98% of the tokens your AI agents spend using MCP tools — without losing anything.
Server | Tools | Before | After | Reduction |
filesystem (Anthropic) | 14 | 1,892 tok | 236 tok | −88% |
sequential-thinking | 1 | 926 tok | 20 tok | −98% |
Google Calendar | 5 | 5,010 tok | 660 tok | −87% |
Enterprise (Cal + Gmail + Drive) | 12 | 8,649 tok | 882 tok | −90% |
sample_app.js (JavaScript) | — | 799 tok | 284 tok | −64.5% |
sample_app.ts (TypeScript) | — | 378 tok | 266 tok | −29.6% |
ast_extractor.py (Python) | — | 3,633 tok | 890 tok | −75.5% |
Fewer tokens sent = lower API bills, faster responses. And nothing is lost. Every check confirmed tools stay 100% usable after compression.
Reproduce these numbers yourself — every input is a static fixture in the repo, tokens counted with tiktoken cl100k_base:
python benchmarks/run_benchmark.py # the table above
python benchmarks/run_benchmark.py --json # machine-readable
python benchmarks/run_benchmark.py --fixture path/to/your_schemas.jsonRelated MCP server: Bifrost-MCP Gateway
One-liner (macOS / Linux) — installs the package and configures Claude Desktop:
curl -sSL https://raw.githubusercontent.com/LoudiliMed/Refract/main/install-refract.sh | shPiping a script from the internet into your shell deserves a quick look first: inspect install-refract.sh on GitHub. It never uses sudo.
Or with pip directly:
pip install refract-mcpfastembed and tree-sitter are installed by default.
Sits between your agent and any MCP server. Compresses tool schemas on the fly so your agent does not load the full catalogue on every request.
Local subprocess (stdio):
refract-proxy --target "npx @modelcontextprotocol/server-filesystem /tmp" --verboseRemote HTTP/SSE server:
# --url implies SSE transport (explicit, recommended for remote endpoints)
refract-proxy --url https://my-mcp-server.com/sse
# or with --transport flag (auto-detection can be overridden)
refract-proxy --target https://my-mcp-server.com/sse --transport sseProxy flags:
Flag | Default | Description |
| required | MCP target: stdio command, HTTP URL, or JSON file |
| — | Alias for |
| — | Remote SSE/HTTP endpoint — implies |
| auto | Force transport to the target: |
| 30 | Connection timeout for SSE targets (retries 3×) |
| stdio | How the proxy serves your agent |
| 8080 | Proxy listen port in |
| off | Print token counts per request |
| WARNING | DEBUG / INFO / WARNING / ERROR |
Add it to Claude Desktop:
{
"mcpServers": {
"my-server-via-refract": {
"command": "/path/to/refract-proxy",
"args": [
"--target",
"npx @modelcontextprotocol/server-filesystem /path/to/folder",
"--verbose"
]
}
}
}For a remote MCP server (SSE):
{
"mcpServers": {
"remote-via-refract": {
"command": "/path/to/refract-proxy",
"args": ["--url", "https://my-mcp-server.com/sse"]
}
}
}Instead of editing entries one by one (or running refract-install per server), refract-wrap-all rewrites all stdio servers in claude_desktop_config.json to go through refract-proxy in a single command:
# Preview what would change — writes nothing
refract-wrap-all --dry-run
# Wrap every stdio server not already going through refract
refract-wrap-all
# Restore the original commands
refract-wrap-all --unwrapExample: this entry
{
"mcpServers": {
"filesystem": {
"command": "npx",
"args": ["@modelcontextprotocol/server-filesystem", "/tmp"],
"env": {"MY_VAR": "1"}
}
}
}becomes
{
"mcpServers": {
"filesystem": {
"command": "/path/to/refract-proxy",
"args": ["--stdio-cmd", "npx @modelcontextprotocol/server-filesystem /tmp"],
"env": {"MY_VAR": "1"}
}
}
}Guarantees:
A backup of the config is taken before every write (claude_desktop_config.json.bak, then .bak2, .bak3… — an existing backup is never overwritten).
env, cwd and any other server fields are preserved.
Servers already going through refract-proxy or refract-server are skipped (already wrapped).
Remote SSE/HTTP servers (url entries) are skipped — only stdio servers are wrapped.
--unwrap is an exact round-trip: wrap then unwrap restores every original command, args and fields.
Flag | Value | Description |
| Streamable HTTP | Current standard (MCP spec 2025-03-26). Use with remote MCP servers. |
| SSE | Legacy transport, kept for compatibility. Use if the server does not support Streamable HTTP. |
| stdio subprocess | Local command (default when |
(omit) | auto-detect | Inferred from |
Both sse and http require an HTTP(S) URL in --target.
# Connect to a remote MCP server via Streamable HTTP (recommended)
refract-proxy --target "https://my-mcp-server.com/mcp" --transport http
# Connect via SSE (legacy)
refract-proxy --target "https://my-mcp-server.com/sse" --transport sse
# Local subprocess (auto-detected, --transport stdio optional)
refract-proxy --target "npx @modelcontextprotocol/server-filesystem /tmp"Exposes your codebase as an MCP server. Your agent can index a repo, get compressed file context, expand specific functions, analyze impact, detect breaking changes, and map security risks.
refract-server --root /path/to/your/repoAdd it to Claude Desktop:
{
"mcpServers": {
"refract-code": {
"command": "/path/to/refract-server",
"args": ["--root", "/path/to/your/repo"]
}
}
}Imagine a library with 50 books.
Without Refract: your agent gets a detailed summary of all 50 books on every question, even if the answer only needs one of them.
With Refract: your agent first gets a list of titles (the index). Once it knows which book it needs, it only receives that book's content.
Technically:
The index (always sent): just tool names and a short description of each.
The detail (sent only when needed): the full description of the tool actually used, everything required to use it correctly, nothing more.
The verification: after every compression, Refract automatically checks that nothing important was removed. If there is any doubt, it sends the full version instead of taking a risk.
No AI model is involved in this process. It is fully automatic, fast, and deterministic.
Tool | What it does |
Compression | Compresses tool schemas on the fly, up to 98% reduction |
Signal check | Verifies callable contract after every compression |
Semantic routing | Identifies the right tool using embeddings (opt-in) |
Prompt caching | Injects Anthropic cache_control for repeated requests |
Tool | Input | Output |
index_repo | repo path | aggregated index of all Python, JS, TS files |
get_compressed | file path | compressed structure + token stats |
expand | file path + function names | verbatim source + dependency context |
blast_radius | file path + function name | all functions that break if target changes |
semantic_diff | file path + old source + new source | breaking changes vs body-only changes |
semantic_diff_branches | repo path + file + function + base/head git refs | semantic_diff of one function between two branches/commits |
security_surface | repo path | map of dangerous calls (subprocess, eval, pickle, requests) |
refract-status --root /path/to/repo
refract-status --root /path/to/repo --jsonFlag | Description |
| Path to analyse (default: current directory) |
| Machine-readable output |
Shows: files per language, raw vs compressed tokens, functions/classes indexed, dangerous calls by category, languages without tree-sitter support.
Ask Claude which functions break if you change a target function.
Example result:
{
"target": "authenticate",
"direct_callers": ["login_user"],
"all_impacted": ["login_user", "verify_session", "admin_access"],
"impacted_count": 3,
"risk_level": "MEDIUM"
}Risk levels: LOW (0 to 2 impacted), MEDIUM (3 to 5), HIGH (6 or more).
Detects breaking API changes by comparing function interfaces, not bodies. Use it as a CI gate.
Example result:
{
"breaking": ["authenticate"],
"body_only": ["logout"],
"added": ["new_function"],
"removed": [],
"unchanged": ["hash_password"],
"is_breaking": true
}If is_breaking is true, the PR changes the public API and must be reviewed.
Maps every function that calls dangerous primitives across your repo.
HIGH risk: subprocess, os.system, eval, exec, pickle, ctypes
MEDIUM risk: open (write mode), socket, requests, httpx, urllib
Example result:
{
"high_risk": [
{
"file": "src/refract_server.py",
"function": "_git_show",
"calls": ["subprocess.run"],
"line_hint": "line 801"
}
],
"medium_risk": [
{
"file": "src/compression_cache.py",
"function": "store_cached",
"calls": ["open"],
"line_hint": "line 90"
},
{
"file": "src/refract_proxy.py",
"function": "_check_url_reachable",
"calls": ["urllib.request.urlopen"],
"line_hint": "line 430"
}
],
"summary": {
"high_risk_count": 1,
"medium_risk_count": 2,
"total_functions_scanned": 789,
"total_files_scanned": 41,
"clean_files": 37
}
}Python (via ast module), JavaScript, TypeScript, JSX, TSX (via tree-sitter). fastembed and tree-sitter are installed by default.
Language is auto-detected from file extension.
Refract integrates with Anthropic prompt caching. as_anthropic_tools() returns compressed tools in Anthropic API format with cache_control pre-injected on the last tool, so the Anthropic API caches the full tool list from the second call onward (price: $0.30/M vs $3.00/M for cache hits).
from refract_proxy import RefractProxy
proxy = RefractProxy(target_url="https://my-mcp-server.com/mcp", use_cache=True)
await proxy.connect()
# Pass directly to the Anthropic client:
response = anthropic_client.messages.create(
model="claude-sonnet-4-6",
tools=proxy.as_anthropic_tools(), # cache_control injected automatically
messages=[{"role": "user", "content": "..."}],
)"Failed to spawn process: No such file or directory" in Claude Desktop
Claude Desktop cannot find refract-proxy in its PATH. Find the absolute path and use it directly:
which refract-proxyThen use the full path in claude_desktop_config.json:
{
"mcpServers": {
"my-tool-via-refract": {
"command": "/full/path/to/refract-proxy",
"args": [
"--target",
"npx @modelcontextprotocol/server-filesystem /path/to/folder"
]
}
}
}Claude Desktop, Cursor, any client that follows the MCP standard, any existing MCP server.
MIT — free to use, including commercially.
Reverse-call-graph impact analysis for a Python function: BFS over inverted call edges to find every function transitively affected by changing target_function. Returns direct_callers, all_impacted, impacted_count, total_functions and a risk_level. Python files only.
| Name | Required | Description | Default |
|---|---|---|---|
| file_path | Yes | Path to a .py file (relative to --root or absolute). | |
| target_function | Yes | Function/method name to analyze the blast radius of. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description fully discloses behavior: BFS algorithm, inverted call edges, returns specific fields (direct_callers, all_impacted, etc.), and scope (Python files only). No hidden side effects or destructive actions are implied.
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-loads the purpose, and includes all essential information without verbosity. 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?
Given no annotations or output schema, the description covers purpose, algorithm, input parameters, return fields, and file type restriction. It is complete for an agent to understand and use this tool correctly.
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% (both params described), so baseline is 3. The description adds value by explaining the algorithm context (BFS over inverted call edges) and linking the parameters to the analysis process, though the schema already defines them clearly.
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 'Reverse-call-graph impact analysis for a Python function', specifying the verb (analyze impact), resource (Python function), and methodology (BFS over inverted call edges). It distinguishes from sibling tools like index_repo and security_surface which have 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 implicitly defines usage: when you need to know which functions are affected by changing a target function in a Python file. It does not explicitly compare with siblings, but the context is clear. The restriction 'Python files only' provides a clear constraint, earning a 4.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Given function/class names in a .py file, return them verbatim (full source) plus their compressed dependency context.
| Name | Required | Description | Default |
|---|---|---|---|
| targets | Yes | Function/class names to expand. | |
| file_path | Yes | Path to a .py file (relative to --root or absolute). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations are absent, so description carries full burden. It states it returns 'full source' and 'compressed dependency context', which is a key behavioral trait. However, it does not disclose read-only nature, auth requirements, or potential performance implications (e.g., large files). 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?
Single sentence, front-loaded with purpose. No wasted words; all information is necessary and directly conveys the tool's action and output.
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 there is no output schema and no annotations, the description is somewhat vague about the exact format of 'compressed dependency context'. While the tool is simple, the description could be more complete by clarifying what 'compressed' means. Sufficient but leaves room for ambiguity.
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 schema already documents both parameters adequately. The tool description adds no new meaning beyond restating the schema descriptions, meeting the baseline but not adding value.
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 uses specific verb 'expand' on function/class names in a .py file, clearly indicating it returns full source plus dependency context. Differentiates from siblings like 'get_compressed' (which likely returns compressed content) and 'blast_radius' (impact analysis).
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 versus alternatives like 'get_compressed' or 'blast_radius'. Usage is implied by the description (to get full source of specific definitions with dependencies), but lacks when-not-to-use or prerequisite information.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
S5-compress a single source file — Python or JS/TS (signatures + dependency contracts, bodies stripped) — and return the compressed structure plus token stats (tokens_before, tokens_after, reduction_pct).
| Name | Required | Description | Default |
|---|---|---|---|
| file_path | Yes | Path to a .py file (relative to --root or absolute). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so the description must disclose behaviors. It does not state whether the operation is read-only or modifies files, nor does it mention side effects, auth requirements, or rate limits. The word 'compress' might imply mutation, but the return of a 'compressed structure' suggests the original file is unchanged. This ambiguity is a gap.
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 well-structured sentence. It front-loads the action ('S5-compress a single source file'), specifies file types, details the compression behavior, and lists the output. No unnecessary 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?
Without output schema, the description should explain the return value structure, but it does mention 'compressed structure plus token stats (tokens_before, tokens_after, reduction_pct),' which is helpful. However, it lacks behavioral context (read/write), does not resolve the file type inconsistency, and does not address how this relates to sibling tools like 'expand.' The minimal viable information is present, but gaps reduce 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% (one parameter with description). The description adds that the tool supports Python and JS/TS, but the schema's parameter description says 'Path to a .py file,' which contradicts the broader file types stated in the tool description. This inconsistency misleads the agent and detracts from the value added 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 compresses a single source file (Python or JS/TS) by stripping bodies while keeping signatures and dependency contracts, and returns token stats. The verb 'compress' and resource 'source file' are specific, and it distinguishes from siblings like 'blast_radius' or 'expand' implicitly.
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 versus alternatives. The description does not mention when to choose compression over expansion or other sibling tools, leaving the agent without decision context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Walk a repo (Python + JavaScript/TypeScript) and return an aggregated structural index: every function, class, import and dependency. Max depth 3; skips pycache, .git, venv, node_modules.
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | Repo path (relative to --root or absolute). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It discloses maximum depth 3 and skipped directories (__pycache__, .git, venv, node_modules), but fails to mention behavior for unsupported file types, invalid paths, or performance implications for large repos. Additional context would improve 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 two concise sentences with front-loaded purpose and clear constraints. Every word adds value, no redundancy.
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, the description partially explains return value as 'aggregated structural index' listing functions, classes, imports, dependencies. However, it lacks details on output format (e.g., JSON structure, list vs. dict) and does not address edge cases like empty repos or mixed languages. It is acceptable but not fully 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 coverage is 100% with a single required 'path' parameter described adequately. The description adds no extra parameter details beyond the schema, so baseline 3 is appropriate. The description's main value is in explaining the tool's overall function, not parameter specifics.
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 walks a repo and returns a structural index of functions, classes, imports, and dependencies, explicitly specifying supported languages (Python and JavaScript/TypeScript). This distinguishes it from sibling tools like 'blast_radius' or 'security_surface', which likely have 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 does not provide explicit guidance on when to use this tool versus alternatives like 'blast_radius' or 'expand'. It only implies usage for structural indexing, but lacks when-to-use, when-not-to-use, or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Walk a Python repo and find functions that call dangerous primitives — pure AST analysis, zero LLM calls. Classifies calls as HIGH risk (subprocess/os.system/eval/exec/pickle/import/ctypes …) or MEDIUM risk (sockets/requests/httpx/urllib/paramiko/smtplib and write-mode open()). Also scans for potential secrets: hardcoded keys/tokens (AKIA…, sk-…, ghp_…, token=/password=/api_key= assignments), .env/environment loading, and high-entropy token-looking literals. Returns high_risk, medium_risk, secrets, clean files and a summary. Max depth 3; skips pycache, .git, venv, node_modules.
| Name | Required | Description | Default |
|---|---|---|---|
| repo_path | Yes | Repo path (relative to --root or absolute). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It clearly states pure AST analysis, zero LLM calls, risk classification levels, secret detection, max depth 3, and skipped directories. Could mention whether the tool is read-only (likely yes) but overall quite transparent.
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?
Description is front-loaded with the main action and packed with relevant details in three sentences. Minimal redundancy, though length could be trimmed slightly without losing meaning.
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, description adequately explains return values (high_risk, medium_risk, secrets, clean files, summary). Covers key behaviors and limitations. Could mention file type filtering but sufficient for an agent to understand scope.
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?
Only one parameter (repo_path) with 100% schema coverage. Description adds no extra detail beyond the schema's description of the path. Baseline score 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?
Description clearly states it walks a Python repo using AST analysis to find dangerous function calls and secrets, with specific risk classifications. No sibling tool overlaps, making its unique purpose unmistakable.
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 (security scanning of Python repos) but does not explicitly state when not to use or mention alternatives among siblings. More precise guidance would improve this dimension.
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.
v0.7.0blast_radiusexpandget_compressedindex_reposecurity_surfaceEach tool has a distinct purpose: impact analysis, source retrieval, file compression, repo indexing, and security scanning. No two tools overlap in functionality.
All tools use snake_case, but 'expand' is a lone verb while others follow a verb_noun pattern (e.g., get_compressed, index_repo). Minor inconsistency but still clear.
5 tools is a well-scoped set for a static analysis toolkit. Neither too few nor too many, each tool serves a clear need.
Covers core static analysis needs (impact, source, compression, indexing, security). Missing a dedicated diff or test analysis tool, but the surface is reasonably complete for the domain.
The OpenRouter for tools. One MCP connection gives any AI agent 254 hosted tools, pay per call.
One MCP endpoint for Claude, GPT & Gemini: 100+ tools + no-code connectors + agent workers.
Security & DLP proxy for MCP: tool-poisoning scans, PII redaction on tool args/results. Beta.
Pay-per-use tool marketplace for AI agents. Search, price-check, and call APIs via MCP.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/LoudiliMed/Refract'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
