TeaRAGs MCP provides AST-aware chunking, vector embeddings, and git-blame–enriched metadata to enable fast, explainable RAG over large repositories. The architecture is designed to evolve toward explicit code topology (L3) and higher reasoning layers.
TeaRAGs
Trajectory Enrichment-Aware RAG for Coding Agents
MCP server for semantic code search with git trajectory reranking. AST-aware chunking, incremental indexing, millions of LOC. Reranks results using authorship, churn, bug-fix rates, and 19 other signals — not just embedding similarity. Built on Qdrant. Works with Ollama (local) or cloud providers (OpenAI, Cohere, Voyage).
📖 Full documentation — 15-minute quickstart, agent workflows, architecture deep dives.
🧬 Trajectory Enrichment
Standard code RAG retrieves by similarity alone. Trajectory enrichment augments each chunk with signals about how code evolves — at the function level, not just file level.
- 🔀 Git trajectory — churn, authorship, volatility, bug-fix rates, task traceability. 19 signals feed composable rerank presets (
hotspots,ownership,techDebt,securityAudit...) - 🕸️ Topological trajectory (planned) — symbol graphs, cross-file coupling, blast radius
Opt-in via CODE_ENABLE_GIT_METADATA=true. Without it — standard semantic search with AST-aware chunking.
💡 An agent can find stable templates, avoid anti-patterns, match domain owner's style, and assess modification risk — all backed by empirical data. Read more →
🚀 Quick Start
git clone https://github.com/artk0de/TeaRAGs-MCP.git
cd TeaRAGs-MCP
npm install && npm run build
# Start Qdrant + Ollama
podman compose up -d
podman exec ollama ollama pull unclemusclez/jina-embeddings-v2-base-code:latest
# Add to Claude Code
claude mcp add tea-rags -s user -- node /path/to/tea-rags-mcp/build/index.js \
-e QDRANT_URL=http://localhost:6333 \
-e EMBEDDING_BASE_URL=http://localhost:11434
Then ask your agent: "Index this codebase for semantic search"
📚 Documentation
| | Section | What's inside | |---|---------|---------------| | 🏁 | Quickstart | Installation, first index & query | | ⚙️ | Configuration | Env vars, providers, tuning | | 🤖 | Agent Integration | Prompt strategies, generation modes, deep analysis | | 🏗️ | Architecture | Pipeline, data model, reranker internals |
🤝 Contributing
See CONTRIBUTING.md for workflow and conventions.
🙏 Acknowledgments
Built on a fork of mhalder/qdrant-mcp-server — clean architecture, solid tests, open-source spirit. And its ancestor qdrant/mcp-server-qdrant. Code vectorization inspired by claude-context (Zilliz).
Feel free to fork this fork. It's forks all the way down. 🐢