๐ Swarms MCP Documentation Server
@Ransom-Alpha
MCP server to connect AI agents to any github corpa
ๆฆ่ง
What is ๐ Swarms MCP Documentation Server?
An MCP server built on FastMCP that enables AI agents to efficiently retrieve information from local documentation repositories. It uses hybrid semantic (vector) and keyword (BM25) search, chunked indexing, and FastMCP tools for seamless agent integration. Designed for developers working with agent frameworks like Swarms, Autogen, LangGraph, and OpenAI Agent SDK.
How to use ๐ Swarms MCP Documentation Server?
Clone documentation repos into the corpora/ folder, install Python 3.11 dependencies from requirements.txt, set an OPENAI_API_KEY in .env, run python embed_documents.py to load and embed documents, then start the server with python swarms_server.py. For IDE integration, add a Windsurf Cascade configuration pointing to the server script and access tools like swarm_docs.search.
Key features of ๐ Swarms MCP Documentation Server
- Hybrid retriever combining semantic and keyword search
- Dynamic Markdown loading based on file size
- Specialized loaders for .py, .ipynb, .md, .txt, .yaml, .yml
- Live file watchdog that auto-reindexes on changes to corpora/
- Healthcheck endpoint to verify server readiness
- User confirmation before expensive embedding operations
Use cases of ๐ Swarms MCP Documentation Server
- AI agents searching large framework documentation for relevant code chunks
- Listing all indexed files across multiple cloned codebases
- Retrieving specific document chunks by path and index for context
- Forcing a full or incremental reindex when documentation changes
- Checking server health before integrating with an agent pipeline
FAQ from ๐ Swarms MCP Documentation Server
Why do I get 'No valid existing index found' when starting the server?
The server will prompt you to embed and index documents automatically. Accept the prompt, or run python embed_documents.py manually first.
Which index file is used for Chroma vector storage?
The server prefers chroma-collections.parquet if available; otherwise it falls back to chroma.sqlite3.
How can I force a reindex of the documentation?
Run python swarms_server.py --reindex or use the swarm_docs.reindex tool. For a full schema refresh, add --full.
How do I add new documentation or repos?
Place the new repository or files inside the corpora/ folder, then reindex with the --reindex flag or the corresponding tool.
What are the runtime requirements?
Python 3.11 environment with dependencies from requirements.txt, an OpenAI API key, and local storage for the Chroma vector database. No external cloud services are required beyond the embedding API call.
