MCP server/search

Tea RAGs MCP Server

Trajectory Enrichment-Aware RAG for Coding Agents

★ 10artk0de/TeaRAGs-MCP ↗by artk0deupdated
Manual setup required. The maintainer's config contains paths only you know - edit the placeholders below before adding it to Claude Code.
1

Prepare the server locally

Run this once before adding it to Claude Code.

git clone https://github.com/artk0de/TeaRAGs-MCP.git
cd TeaRAGs-MCP
npm install
npm run build
2

Register it in Claude Code

claude mcp add -e "QDRANT_URL=${QDRANT_URL}" -e "EMBEDDING_BASE_URL=${EMBEDDING_BASE_URL}" tea-rags -- node /path/to/tea-rags/build/index.js

Replace any placeholder paths in the command with the real path on your machine.

Required:QDRANT_URLEMBEDDING_BASE_URL+ 1 optional
3

Make your agent remember this setup

tea-rags's config, env vars, and the gotchas you hit — recalled in every future Claude Code, Cursor, and Codex session.

npx conare@latest

Free · one command · indexes the sessions already on disk. Set up in the browser instead →

What it does

  • Git trajectory reranking using 19 signals like churn, authorship, and bug-fix rates.
  • AST-aware chunking for precise code context retrieval.
  • Incremental indexing support for large codebases.
  • Provider-agnostic support for local (Ollama) or cloud embedding models.
  • Qdrant-backed vector storage for high-performance search.

Tools 2

index_codebaseIndexes the codebase for semantic search and trajectory analysis.
search_codePerforms semantic search with git trajectory reranking.

Environment Variables

QDRANT_URLrequiredThe URL of the Qdrant vector database instance.
EMBEDDING_BASE_URLrequiredThe base URL for the embedding provider (e.g., Ollama).
CODE_ENABLE_GIT_METADATAEnables git trajectory enrichment (churn, authorship, etc.).

Try it

Index this codebase for semantic search.
Find code snippets related to authentication that have high bug-fix rates.
Search for stable templates in the project using the 'hotspots' reranking preset.
Identify potential technical debt in the current directory.
Original README from artk0de/TeaRAGs-MCP
<a href="https://artk0de.github.io/TeaRAGs-MCP/"> </a> <h1 align="center">TeaRAGs</h1>

<strong>Trajectory Enrichment-Aware RAG for Coding Agents</strong>


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/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

artk0de.github.io/TeaRAGs-MCP

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. 🐢

⚖️ License

MIT — see LICENSE. Brand policy in BRAND.md.

Frequently Asked Questions

What are the key features of Tea RAGs?

Git trajectory reranking using 19 signals like churn, authorship, and bug-fix rates.. AST-aware chunking for precise code context retrieval.. Incremental indexing support for large codebases.. Provider-agnostic support for local (Ollama) or cloud embedding models.. Qdrant-backed vector storage for high-performance search..

What can I use Tea RAGs for?

Finding stable code templates to avoid introducing new bugs.. Identifying high-risk code areas for security audits.. Matching code style based on domain owner's historical contributions.. Assessing modification risk before refactoring complex modules..

How do I install Tea RAGs?

Install Tea RAGs by running: git clone https://github.com/artk0de/TeaRAGs-MCP.git && cd TeaRAGs-MCP && npm install && npm run build

What MCP clients work with Tea RAGs?

Tea RAGs works with any MCP-compatible client including Claude Desktop, Claude Code, Cursor, and other editors with MCP support.

Conare · memory for coding agents

Turn this server into reusable context

Keep Tea RAGs docs, env vars, and workflow notes in Conare so your agent carries them across sessions.

Set up free$npx conare@latest