Rust Docs Server
Fetches Rust crate documentation from docs.rs using the rustdoc JSON API.
Docs.rs MCP Server
A Model Context Protocol (MCP) server for fetching Rust crate documentation from docs.rs
Features • Getting Started • Tools • Contributing • Acknowledgments • License
Features
- Find New Crates - Search crates by exact name, partial match, or fuzzy query to discover relevant libraries
- Inspect Crate Symbols - Inspect structs, traits, functions, and any other symbol inside a crate
- Review Crate Summaries - Get a crate overview with its structure and public API surface
- Read Full Documentation - Read crate-level documentation
Getting Started
Using Pre-built Executables
Download the latest release for your platform from the Releases page:
Linux
- x64/AMD64 (GLIBC):
mcp-docsrs-linux-x64- For Ubuntu, Debian, Fedora, etc. - ARM64 (GLIBC):
mcp-docsrs-linux-arm64- For ARM64 systems, AWS Graviton - x64/AMD64 (MUSL):
mcp-docsrs-linux-x64-musl- For Alpine Linux, Docker containers (requires libstdc++) - ARM64 (MUSL):
mcp-docsrs-linux-arm64-musl- For Alpine on ARM64, minimal containers (requires libstdc++)
macOS
- Intel:
mcp-docsrs-darwin-x64- For Intel-based Macs - Apple Silicon:
mcp-docsrs-darwin-arm64- For M-series Macs
Windows
- x64:
mcp-docsrs-windows-x64.exe- For 64-bit Windows
Using Docker
Pull and run the latest multi-arch image (supports both x64 and ARM64):
# Pull the latest image
docker pull ghcr.io/vexxvakan/mcp-docsrs:latest
# Run the server
docker run --rm -i ghcr.io/vexxvakan/mcp-docsrs:latest
# Run with custom configuration
docker run --rm -i ghcr.io/vexxvakan/mcp-docsrs:latest \
--cache-ttl 7200000 --max-cache-size 200
Available tags:
latest- Latest stable release (multi-arch)v1.0.0- Specific version (multi-arch)
MCP Setup
| Client | Command |
|---|---|
| Codex | codex mcp add docsrs -- path/to/mcp-docsrs |
| Claude Code | claude mcp add --transport stdio docsrs -- path/to/mcp-docsrs |
| Gemini CLI | gemini mcp add -s user docsrs path/to/mcp-docsrs |
| OpenCode | Run opencode mcp add, choose a local MCP server, then point it at path/to/mcp-docsrs. |
| VS Code | Open Command Palette (Cmd/Ctrl+Shift+P) → MCP: Add Server → choose Workspace or User → Command (stdio) → enter path/to/mcp-docsrs. |
| Cursor | Open Settings (Cmd/Ctrl+Shift+J) → Tools & Integrations → New MCP Server → choose a local/stdio server → enter path/to/mcp-docsrs. |
After adding the server, restart the client if it does not discover the tools immediately.
Configuration
Configure the server using environment variables or command-line arguments:
| Variable | CLI Flag | Default | Description |
|---|---|---|---|
CACHE_TTL | --cache-ttl | 3600000 | Cache time-to-live in milliseconds |
MAX_CACHE_SIZE | --max-cache-size | 100 | Maximum number of cached entries |
REQUEST_TIMEOUT | --request-timeout | 30000 | HTTP request timeout in milliseconds |
DB_PATH | --db-path | :memory: | Path to SQLite database file |
Tools
The server exposes four MCP tools:
Crate
crate_lookup
Retrieves a crate overview with its structure and public API surface from docs.rs.
| Parameter | Type | Required | Description |
|---|---|---|---|
crateName | string | Yes | Name of the Rust crate to inspect |
version | string | No | Specific version or semver range, for example "1.0.0" or "~4" |
target | string | No | Target platform, for example "i686-pc-windows-msvc" |
formatVersion | number | No | Rustdoc JSON format version |
{
"tool": "crate_lookup",
"arguments": {
"crateName": "tokio",
"version": "1.48.0"
}
}
crate_docs
Retrieves the crate-level documentation page from docs.rs.
| Parameter | Type | Required | Description |
|---|---|---|---|
crateName | string | Yes | Name of the Rust crate to inspect |
version | string | No | Specific version or semver range, for example "1.0.0" or "~4" |
target | string | No | Target platform, for example "i686-pc-windows-msvc" |
formatVersion | number | No | Rustdoc JSON format version |
{
"tool": "crate_docs",
"arguments": {
"crateName": "serde"
}
}
crate_find
Searches crates.io for matching crates and returns ranked results using fuzzy and partial name matching.
| Parameter | Type | Required | Description |
|---|---|---|---|
query | string | Yes | Search query for crate names |
limit | number | No | Maximum number of results to return. Defaults to 10 |
{
"tool": "crate_find",
"arguments": {
"query": "rustdoc json",
"limit": 5
}
}
Symbol
symbol_lookup
Retrieves structured symbol metadata for one symbol inside a crate.
| Parameter | Type | Required | Description |
|---|---|---|---|
crateName | string | Yes | Name of the Rust crate |
symbolType | string | Yes | Rustdoc symbol type, for example "struct", "function", or "trait" |
symbolname | string | Yes | Symbol name or path, for example "runtime::Runtime" or "spawn" |
version | string | No | Specific version or semver range |
target | string | No | Target platform |
{
"tool": "symbol_lookup",
"arguments": {
"crateName": "tokio",
"symbolType": "struct",
"symbolname": "runtime::Runtime"
}
}
symbol_docs
Retrieves the full documentation body for one symbol inside a crate.
| Parameter | Type | Required | Description |
|---|---|---|---|
crateName | string | Yes | Name of the Rust crate |
symbolType | string | Yes | Rustdoc symbol type, for example "struct", "function", or "trait" |
symbolname | string | Yes | Symbol name or path, for example "runtime::Runtime" or "spawn" |
version | string | No | Specific version or semver range |
target | string | No | Target platform |
{
"tool": "symbol_docs",
"arguments": {
"crateName": "tokio",
"symbolType": "struct",
"symbolname": "runtime::Runtime"
}
}
Contributing
- See CONTRIBUTING.md.
- See TESTING.md.
Acknowledgments
- docs.rs for providing the Rust documentation API
- Model Context Protocol for the MCP specification
- The Rust community for excellent documentation standards
License
This project is licensed under the Apache License 2.0. See LICENSE for the license text and NOTICE for attribution details.
Made with ❤️ for the Rust community
相关服务器
Alpha Vantage MCP Server
赞助Access financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more
codesight
CLI token optimizer and AI context generator with built-in MCP server. Scans codebases to extract routes, schema, components, and dependencies 9x–13x token reduction for Claude Code, Cursor, Copilot, Codex, and Windsurf.
BloodHound-MCP
integration that connects BloodHound with AI through MCP, allowing security professionals to analyze Active Directory attack paths using natural language queries instead of Cypher.
Feishu MCP Server
An MCP server with built-in Feishu OAuth authentication, deployable on Cloudflare Workers.
302AI Sandbox MCP Server
A code sandbox for AI assistants to safely execute arbitrary code. Requires a 302AI API key for authentication.
Autoconsent MCP
A server for browser automation to create and test Autoconsent rules for web page consent management.
JetBrains
Work on your code with JetBrains IDEs
MCP-Booster
An MCP server with CoConuT (Continuous Chain of Thought) for use with the Cursor IDE, distributed as a global NPM package.
Remote MCP Server (Authless)
An example of a remote MCP server deployable on Cloudflare Workers without authentication.
Biel.ai MCP Server
Connect AI tools like Cursor and VS Code to your product documentation using the Biel.ai platform.
Homebrew MCP
Interact with Homebrew (the package manager for macOS and Linux) using natural language commands.