rust-docs-mcp-server🦀 Prevents outdated Rust code suggestions from AI assistants. This MCP server fetches current crate docs, uses embeddings/LLMs, and provides accurate context via a tool call.

The rust-docs-mcp-server is a tool designed to provide AI-powered coding assistants with up-to-date knowledge of Rust crates. It addresses the issue of outdated code suggestions by fetching current crate documentation, generating embeddings, and providing accurate context via tool calls. This server is particularly useful for crates with frequently updated APIs, such as those found in the Rust ecosystem. By running an instance of this server for a specific crate, developers can give their LLM coding assistant a focused knowledge source to improve the accuracy and relevance of generated code. The server supports multiple instances, allowing access to documentation for several crates during a coding session. It uses OpenAI models for text embeddings and LLM summarization. The server caches generated documentation content and embeddings locally to speed up subsequent launches. Overall, it aims to reduce the need for manual correction and speed up development by providing timely and accurate API information.