mcp-codesearch

michaelkrauty/mcp-codesearch
★ 1 stars Python AI/LLM Updated today
MCP server for semantic code search — AST-aware chunking, hybrid dense+sparse search, 160+ languages
View on GitHub → Try with Claude — $10 free →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "mcp-codesearch": {
      "command": "uvx",
      "args": [
        "mcp-codesearch"
      ]
    }
  }
}

Or install with pip: pip install mcp-codesearch

README Excerpt

MCP server for semantic code search with AST-aware chunking, hybrid vectors, and query syntax. - **Python 3.12+** - **Linux or macOS** (uses POSIX file locking via vector-core; not compatible with Windows) - [Qdrant](https://qdrant.tech/) vector database (default: `localhost:6333`) - An OpenAI-compatible embedding API (e.g., llama.cpp, Ollama, or any `/v1/embeddings` endpoint; default: `localhost:8080`)

Tools (20)

CODESEARCH_CHUNK_MAX_LINESCODESEARCH_CHUNK_MIN_LINESCODESEARCH_CHUNK_OVERLAP_LINESCODESEARCH_CLASS_SPLIT_THRESHOLDCODESEARCH_DELETION_CONCURRENCYCODESEARCH_SEARCH_CACHE_EVICTION_RATIOCODESEARCH_SEARCH_CACHE_MAX_SIZECODESEARCH_SEARCH_CACHE_TTL_SECONDSCODESEARCH_UPSERT_BATCH_TIMEOUTCODESEARCH_UPSERT_CONCURRENCYVECTOR_EMBEDDING_DIMVECTOR_EMBEDDING_MODELVECTOR_EMBEDDING_URLVECTOR_QDRANT_URLauthorizationbothchunkcleanup_orphanscode_searchdatabase

Topics

claudecode-searchmcpmcp-serverpythonqdrantsemantic-searchtree-sitter