π Swarms MCP Documentation Server
About
MCP server to connect AI agents to any github corpa
Details
- Author
- Ransom-Alpha
- Downloads
- 252
- Categories
- Knowledge Base, AI
Jump to
- 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
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
π Swarms MCP Documentation ServerCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
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.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"\ud83d\udc1d swarms mcp documentation server": {
"Swarms_MCPserver": {
"command": "python",
"args": [
"swarms_server.py",
"--reindex"
]
}
}
}
}
McpServers
{
"Swarms_MCPserver": {
"command": "python",
"args": [
"swarms_server.py",
"--reindex"
]
}
}
π Swarms MCP Documentation Server
<p align="center">
</p>
---
π Description
This program is an Agent Framework Documentation MCP Server built on FastMCP, designed to enable AI agents to efficiently retrieve information from your documentation database. It combines hybrid semantic (vector) and keyword (BM25) search, chunked indexing, and a robust FastMCP tools API for seamless agent integration.
Key Capabilities:
- Efficient, chunk-level retrieval using both semantic and keyword search
- Agents can query, list, and retrieve documentation using FastMCP tools
- Local-first, low-latency design (all data indexed and queried locally)
- Automatic reindexing on file changes
- Modular: add any repos to corpora/, support for all major filetypes
- Extensible: add new tools, retrievers, or corpora as needed
Main modules:
- embed_documents.py β Loads, chunks, and embeds documents
- swarms_server.py β Brings up the MCP server and FastMCP tools
---
---
π Key Features
- Hybrid Retriever π: Combines semantic and keyword search.
- Dynamic Markdown Handling π: Smart loader based on file size.
- Specialized Loaders βοΈ: .py, .ipynb, .md, .txt, .yaml, .yml.
- Chunk and File Summaries π: Displays chunk counts along with file counts.
- Live Watchdog π₯: Instantly responds to any changes in corpora/.
- User Confirmation for Costs β
: Confirms before expensive embeddings.
- Healthcheck Endpoint π: Ensure server is ready for use.
- Local-First ποΈ: All repos indexed locally without external dependencies.
- Safe Deletion Helper π₯: Auto-delete broken/mismatched indexes.
---
ποΈ Version History
| Version | Date | Highlights |
| ------- | ---------- | ---------------------------------------------------------------------- |
| 2.2 | 2025β04β25 | Split embed/load from server; full chunk counting in loading summaries |
| 1.0 | 2025β04β25 | Dynamic Markdown loader, color logs, Healthcheck tool |
| 0.7 | 2025β04β25 | Specialized file loaders for .py, .ipynb, .md |
| 0.5 | 2025β04β10 | OpenAI large model embeddings, extended MCP tools |
| 0.1 | 2025β04β10 | Initial version with generic loaders |
---
π Managing Your Corpora (Local Repos)
Because Swarms and other frameworks are very large, full corpora are not pushed to GitHub.
Instead, you clone them manually under corpora/:
```bash
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.


