st3v3nmw/sourcerer-mcp

MCP for semantic code search & navigation that reduces token waste

42
/ 100
Emerging

Uses Tree-sitter to parse code into semantic chunks (functions, classes, methods) and generates OpenAI embeddings for each, storing them in a persistent vector database (chromem-go) that automatically syncs with file changes via fsnotify. Exposes MCP tools for semantic search, chunk retrieval, and similarity matching, enabling Claude and other AI clients to query code conceptually rather than scanning entire files. Supports Go, Python, JavaScript, TypeScript, and Markdown with language coverage defined through Tree-sitter queries.

107 stars.

No Package No Dependents
Maintenance 6 / 25
Adoption 9 / 25
Maturity 15 / 25
Community 12 / 25

How are scores calculated?

Stars

107

Forks

11

Language

Go

License

MIT

Last pushed

Nov 10, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/mcp/st3v3nmw/sourcerer-mcp"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.