Govcraft/rust-docs-mcp-server

⭐ **Like this project? Please
star the repository on
GitHub to show your support and stay updated!** ⭐
Motivation
Modern AI-powered coding assistants (like Cursor, Cline, Roo Code, etc.) excel
at understanding code structure and syntax but often struggle with the specifics
of rapidly evolving libraries and frameworks, especially in ecosystems like Rust
where crates are updated frequently. Their training data cutoff means they may
lack knowledge of the latest APIs, leading to incorrect or outdated code
suggestions.
This MCP server addresses this challenge by providing a focused, up-to-date
knowledge source for a specific Rust crate. By running an instance of this
server for a crate (e.g., serde, tokio, reqwest), you give your LLM coding
assistant a tool (query_rust_docs) it can use _before_ writing code related to
that crate.
When instructed to use this tool, the LLM can ask specific questions about the
crate's API or usage and receive answers derived directly from the _current_
documentation. This significantly improves the accuracy and relevance of the
generated code, reducing the need for manual correction and speeding up
development.
Multiple instances of this server can be run concurrently, allowing the LLM
assistant to access documentation for several different crates during a coding
session.
This server fetches the documentation for a specified Rust crate, generates
embeddings for the content, and provides an MCP tool to answer questions about
the crate based on the documentation context.
Features
- **Targeted Documentation:** Focuses on a single Rust crate per server
instance.
- **Feature Support:** Allows specifying required crate features for
documentation generation.
- **Semantic Search:** Uses OpenAI's text-embedding-3-small model to find the
most relevant documentation sections for a given question.
- **LLM Summarization:** Leverages OpenAI's gpt-4o-mini-2024-07-18 model to
generate concise answers based _only_ on the retrieved documentation context.
- **Caching:** Caches generated documentation content and embeddings in the
user's XDG data directory (~/.local/share/rustdocs-mcp-server/ or similar)
based on crate, version, _and_ requested features to speed up subsequent
launches.
- **MCP Integration:** Runs as a standard MCP server over stdio, exposing tools
and resources.
Prerequisites
- **OpenAI API Key:** Needed for generating embeddings and summarizing answers.
The server expects this key to be available in the OPENAI_API_KEY
environment variable. (The server also requires network access to download
crate dependencies and interact with the OpenAI API).
Installation
The recommended way to install is to download the pre-compiled binary for your
operating system from the
GitHub Releases page.
1. Go to the
Releases page.
2. Download the appropriate archive (.zip for Windows, .tar.gz for
Linux/macOS) for your system.
3. Extract the rustdocs_mcp_server (or rustdocs_mcp_server.exe) binary.
4. Place the binary in a directory included in your system's PATH environment
variable (e.g., /usr/local/bin, ~/bin).
Building from Source (Alternative)
If you prefer to build from source, you will need the
Rust Toolchain installed.
1. **Clone the repository:**
2. **Build the server:**
Usage
**Important Note for New Crates:**
When using the server with a crate for the first time (or with a new version/feature set), it needs to download the documentation and generate embeddings. This process can take some time, especially for crates with extensive documentation, and requires an active internet connection and OpenAI API key.
It is recommended to run the server once directly from your command line for any new crate configuration *before* adding it to your AI coding assistant (like Roo Code, Cursor, etc.). This allows the initial embedding generation and caching to complete. Once you see the server startup messages indicating it's ready (e.g., "MCP Server listening on stdio"), you can shut it down (Ctrl+C). Subsequent launches, including those initiated by your coding assistant, will use the cached data and start much faster.