by yannicktm
DocuMCP: RAG documentation server with on-prem semantic search for code, docs, and diagrams — integrates vector DBs with
Generates intelligent documentation for codebases using RAG and semantic search, with optional multi-agent orchestration for large-scale documentation workflows.
DocuMCP (RAG Documentation Server) is a community-built MCP server published by yannicktm that provides AI assistants with tools and capabilities via the Model Context Protocol. DocuMCP: RAG documentation server with on-prem semantic search for code, docs, and diagrams — integrates vector DBs with It is categorized under ai ml, developer tools.
You can install DocuMCP (RAG Documentation Server) in your AI client of choice. Use the install panel on this page to get one-click setup for Cursor, Claude Desktop, VS Code, and other MCP-compatible clients. This server runs locally on your machine via the stdio transport.
MIT
DocuMCP (RAG Documentation Server) is released under the MIT license. This is a permissive open-source license, meaning you can freely use, modify, and distribute the software.
Add new capabilities to Claude beyond text generation
Example
Access external data sources, execute code, interact with tools and services
Transform Claude from chatbot to action-taking agent
Provide Claude with access to relevant context and data
Example
Load project documentation, access knowledge bases, query databases
Get more accurate, context-aware responses
Automate multi-step workflows combining AI and external tools
Example
Research → Summarize → Create document → Send notification
Complete complex tasks end-to-end without manual steps
Share your MCP server with the developer community
We wired DocuMCP (RAG Documentation Server) into a staging workspace; the listing’s GitHub and npm pointers saved time versus hunting across READMEs.
We wired DocuMCP (RAG Documentation Server) into a staging workspace; the listing’s GitHub and npm pointers saved time versus hunting across READMEs.
DocuMCP (RAG Documentation Server) reduced integration guesswork — categories and install configs on the listing matched the upstream repo.
DocuMCP (RAG Documentation Server) is a well-scoped MCP server in the explainx.ai directory — install snippets and categories matched our Claude Code setup.
Useful MCP listing: DocuMCP (RAG Documentation Server) is the kind of server we cite when onboarding engineers to host + tool permissions.
DocuMCP (RAG Documentation Server) is a well-scoped MCP server in the explainx.ai directory — install snippets and categories matched our Claude Code setup.
DocuMCP (RAG Documentation Server) has been reliable for tool-calling workflows; the MCP profile page is a good permalink for internal docs.
DocuMCP (RAG Documentation Server) is among the better-indexed MCP projects we tried; the explainx.ai summary tracks the official description.
We evaluated DocuMCP (RAG Documentation Server) against two servers with overlapping tools; this profile had the clearer scope statement.
DocuMCP (RAG Documentation Server) is among the better-indexed MCP projects we tried; the explainx.ai summary tracks the official description.
showing 1-10 of 57
🤖 A comprehensive MCP system for intelligent code documentation generation with RAG capabilities and multi-agent orchestration
DocuMCP consists of two complementary MCP servers:
Together, they enable Claude to generate, search, and manage documentation for your codebase at any scale, from single files to entire enterprise applications.
The easiest way to use DocuMCP is to configure Claude Desktop with the published npm package:
Add the following to your Claude Desktop configuration:
~/Library/Application Support/Claude/claude_desktop_config.json%APPDATA%/Claude/claude_desktop_config.json{
"mcpServers": {
"docu-mcp": {
"command": "npx",
"args": ["-y", "@myjungle/docu-mcp-server"]
}
}
}
{
"mcpServers": {
"docu-mcp-manager": {
"command": "npx",
"args": ["-y", "@myjungle/docu-mcp-manager"]
}
}
}
Restart Claude Desktop and both servers will be available.
Install the server via Smithery CLI:
# Install Smithery CLI if you don't have it
npm install -g @smithery/cli
# Then install the Docu MCP server
npx -y @smithery/cli@latest install @YannickTM/docu-mcp --client claude
git clone https://github.com/YannickTM/docu-mcp
cd docu-mcp
npm install
# Build DocuMCP Server
cd mcp
npm run build
cd ..
# Build DocuMCP Manager
cd manager
npm run build
cd ..
Add the following to your Claude Desktop configuration:
~/Library/Application Support/Claude/claude_desktop_config.json%APPDATA%/Claude/claude_desktop_config.json{
"mcpServers": {
"docu-mcp": {
"command": "node",
"env": {
"VECTOR_DB_PROVIDER": "qdrant",
"QDRANT_URL": "http://localhost:6333",
"EMBEDDING_PROVIDER": "ollama",
"EMBEDDING_MODEL": "bge-m3:latest",
"EMBEDDING_DIMENSION": "1024",
"OLLAMA_URL": "http://localhost:11434"
},
"args": ["/absolute/path/to/DocuMCP/mcp/dist/index.js"]
},
"docu-mcp-manager": {
"command": "node",
"env": {
"VECTOR_DB_PROVIDER": "qdrant",
"QDRANT_URL": "http://localhost:6333",
"EMBEDDING_PROVIDER": "ollama",
"EMBEDDING_MODEL": "bge-m3:latest",
"EMBEDDING_DIMENSION": "1024",
"OLLAMA_URL": "http://localhost:11434",
"SUB_AGENT_MODEL": "claude-3-7-sonnet-latest"
},
"args": ["/absolute/path/to/DocuMCP/manager/dist/index.js"]
}
}
}
Important: Both servers should use the same vector database configuration to enable shared access.
cd qdrant
npm run start
cd chromadb
npm run start
Restart Claude Desktop to load the new configuration.
| Provider | Description | Configuration |
|---|---|---|
| LanceDB | File-based local database (default) | VECTOR_DB_PROVIDER=lance<br/>LANCE_PATH=~/lanceDB |
| ChromaDB | Simple vector database with web UI | VECTOR_DB_PROVIDER=chroma<br/>CHROMA_URL=http://localhost:8000 |
| Qdrant | Production-grade vector database | VECTOR_DB_PROVIDER=qdrant<br/>QDRANT_URL=http://localhost:6333 |
| Provider | Description | Configuration |
|---|---|---|
| Built-in | Uses all-MiniLM-L6-v2 model (default) | EMBEDDING_PROVIDER=buildin<br/>EMBEDDING_MODEL=all-MiniLM-L6-v2<br/>EMBEDDING_DIMENSION=384 |
| Ollama | Use any Ollama model | EMBEDDING_PROVIDER=ollama<br/>EMBEDDING_MODEL=bge-m3:latest<br/>EMBEDDING_DIMENSION=1024<br/>OLLAMA_URL=http://localhost:11434 |
read_file, write_file, create_directory, read_directorysearch_codebase, search_documentation, search_diagram, search_user_guidegenerate_documentation, generate_user_guide, explain_codegenerate_diagram, merge_diagramindex_file, index_directorymerge_documentationspawn_agent: Create Claude Code sub-agents for documentation tasksmanage_agent: Monitor, control, and retrieve results from agentsContributions are welcome! Please feel free to submit a Pull Request.
Made with ❤️
Prerequisites
Time Estimate
15-60 minutes depending on server complexity
Steps
Troubleshooting
✓ Do
✗ Don't
💡 Pro Tips
Architecture
Model Context Protocol standardizes how AI hosts (Claude, Cursor) communicate with external tools and data sources through server implementations.
Protocols
Compatibility
✓ Use when
Use when you need Claude to access external data, execute actions, or integrate with tools. Best for extending AI capabilities beyond conversation.
✗ Avoid when
Avoid when native integrations exist (use official APIs directly), for real-time critical systems, or when security/compliance requires zero external dependencies.