Semantic Search MCP Server
Provides hybrid semantic and keyword code search for Claude Code using BM25 and vector retrieval. It enables indexing and searching local codebases with language-aware chunking and local embeddings.
README
Semantic Search MCP Server
Semantic code search for Claude Code — powered by hybrid BM25 + vector retrieval.
What It Does
An MCP server that gives Claude Code semantic search over your codebase. Unlike pure vector search, this uses hybrid retrieval (BM25 keyword matching + vector semantic search + Reciprocal Rank Fusion) for significantly better results.
Quick Start
# Install
cd semantic_search_MCP
pip install -e ".[dev]"
# Test the server with MCP inspector
npx @modelcontextprotocol/inspector python -m semantic_search_mcp
# Connect to Claude Code
claude mcp add semantic-search -- python -m semantic_search_mcp
Tools
| Tool | Description |
|---|---|
search(query, repo_path?, top_k?, file_glob?) |
Hybrid semantic + keyword search. Auto-indexes if needed. |
index(repo_path?, force_rebuild?) |
Build or rebuild the search index. |
status(repo_path?) |
Check if a repo is indexed and whether the index is stale. |
Example Usage (inside Claude Code)
> Search for where JWT validation happens
> Index this repository first, then find auth middleware
> Search for error handling in src/api/**
Architecture
- Chunking: Language-aware regex splitting (10 languages) with context headers
- Embeddings:
all-MiniLM-L6-v2via sentence-transformers (local, no API key) - Vector store: LanceDB (serverless, file-based)
- BM25: SQLite FTS5 sidecar
- Retrieval: Hybrid BM25 + vector with RRF merge
Stack
- Python 3.11+
- FastMCP (MCP server framework)
- LanceDB (vector storage)
- sentence-transformers (embeddings)
- SQLite FTS5 (keyword search)
Configuration
Set via environment variables:
| Variable | Default | Description |
|---|---|---|
SEMANTIC_SEARCH_DATA_DIR |
~/.semantic-search/data |
Where indexes are stored |
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.