Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@pipecat-docs-mcp how to use daily transport in a pipeline"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Search 317 pages of Pipecat docs + 1,028 GitHub Issues from Claude Desktop or Cursor — grounded answers, no hallucinated APIs.
Indexes 8,817 chunks from the Pipecat docs and GitHub Issues, then exposes them through 4 MCP tools. Claude can answer questions about configuration, code examples, architecture concepts, and provider comparisons — with source-cited results pulled directly from the official docs and community issue threads.
Retrieval pipeline: BM25 + FAISS dense vectors → Reciprocal Rank Fusion → Cross-encoder reranker
Metric | Value |
Pages indexed | 317 |
GitHub Issues indexed | 1,028 |
Total chunks | 8,817 |
Mean Reciprocal Rank | 0.863 |
Recall@5 | 100% |
Avg query latency | 35ms |
Related MCP server: github-rag-mcp
Tool | Use it when... |
| General questions, config options, error messages |
| You need a runnable Python pipeline |
| "What is a Frame / Pipeline / VAD / Transport?" |
| Choosing between STT, TTS, or transport providers |
git clone https://github.com/DTufail/pipecat-docs-mcp.git
cd pipecat-docs-mcp
python -m venv .venv && source .venv/bin/activate
pip install -r requirements.txtdata/chunks.jsonl is included. This builds the BM25 and FAISS indexes (~2 min):
python indexer.pyAdds 1,028 issues from pipecat-ai/pipecat for error-driven retrieval:
export GITHUB_TOKEN="your_token_here" # optional but recommended (5k req/hr vs 60)
python github_indexer.py
python indexer.py # rebuild indexes with issues mergedAdd to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"pipecat-docs": {
"command": "/absolute/path/to/.venv/bin/python3",
"args": ["/absolute/path/to/pipecat-docs-mcp/server.py"]
}
}
}Use the Python binary from your virtual environment, not system Python. Restart Claude Desktop after saving.
fastmcp run server.py:mcp --transport http --port 8000Point your MCP client at http://localhost:8000/mcp.
pipecat-docs-mcp/
├── server.py # FastMCP server — 4 MCP tools
├── retrieval.py # Hybrid search (BM25 + FAISS + RRF + reranker)
├── indexer.py # Builds BM25, FAISS, and metadata indexes
├── github_indexer.py # Fetches GitHub Issues → data/github_issues.jsonl
├── config.py # Paths and model config
├── test_server.py # In-process tests for all 4 tools
├── test_retrieval.py # Retrieval eval — MRR, Recall@5, latency (17 queries)
├── requirements.txt
├── pipecat-scraper/
│ ├── scraper.py # Sitemap-driven scraper (317 pages, resumable)
│ ├── utils.py # HTML parsing and chunking
│ ├── audit.py # Per-page extraction audit
│ └── config.py
└── data/
├── chunks.jsonl # 6,936 scraped doc chunks (included)
├── chunk_metadata.json # Title, section, URL, content type per chunk
├── bm25_index.pkl # Generated by indexer.py (gitignored)
├── faiss_index.bin # Generated by indexer.py (gitignored)
├── embeddings.npy # Generated by indexer.py (gitignored)
└── github_issues.jsonl # Generated by github_indexer.py (gitignored)To refresh against a newer Pipecat release:
cd pipecat-scraper
python scraper.py # scrapes docs.pipecat.ai → data/chunks.jsonl
cd ..
python indexer.py # rebuilds indexesAuto-refresh on new Pipecat releases via GitHub webhook
Expanded coverage — LiveKit and Vapi docs
MIT
This server cannot be installed
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Search and read Vector Panda docs: API operations, pricing, storage tiers, measured benchmarks.
Get authoritative answers about Redpanda documentation and search API references.
Search the SiteGPT documentation: setup, features, API reference, troubleshooting.
Search the Cerebrium docs: deployment, cerebrium.toml, hardware, endpoints. Also sends feedback.
