rust-code-mcp

An MCP server for semantic code search in Rust codebases. Combines BM25 full-text search with vector embeddings for hybrid search, plus tree-sitter based code analysis.

Architecture

Features

• Hybrid search - BM25 keyword search + semantic vector similarity
• Symbol navigation - Find definitions and references across the codebase
• Call graph analysis - Trace function call relationships
• Complexity metrics - LOC, cyclomatic complexity, function counts
• Incremental indexing - Merkle tree change detection for fast re-indexing
• Background sync - Automatic index updates every 5 minutes

Tools

Tool	Description
search	Keyword search using hybrid BM25 + vectors
get_similar_code	Find semantically similar code snippets
find_definition	Locate where a symbol is defined
find_references	Find all usages of a symbol
get_dependencies	List imports for a file
get_call_graph	Show function call relationships
analyze_complexity	Calculate code complexity metrics
read_file_content	Read file contents
index_codebase	Manually trigger indexing
health_check	Check system status

Prerequisites

A Qdrant instance must be running for vector storage. By default, the server connects to localhost:6334.

# Using Docker
docker run -p 6333:6333 -p 6334:6334 qdrant/qdrant

Building

cargo build --release

Configuration

The server uses stdio transport. Add to your MCP client config:

{
  "mcpServers": {
    "rust-code-mcp": {
      "command": "/path/to/rust-code-mcp"
    }
  }
}

Stack

• tantivy - Full-text search
• fastembed - Local embeddings (ONNX)
• qdrant - Vector storage
• tree-sitter - AST parsing
• rmcp - MCP protocol

License

MIT