Mcp Server Ragdocs

What is Ragdocs?

Ragdocs is an MCP server that provides tools for retrieving and processing documentation through vector search, enabling AI assistants to augment their responses with relevant documentation context.

How to use Ragdocs?

Install and run it via npx -y @sanderkooger/mcp-server-ragdocs. Configure the server with environment variables for your embeddings provider (Ollama or OpenAI) and Qdrant vector database. Add the configuration to your MCP host (e.g., Claude Desktop) using the provided JSON snippets.

Key features of Ragdocs

• Vector-based documentation search and retrieval
• Support for multiple documentation sources
• Local (Ollama) or OpenAI embedding generation
• Automated documentation processing and indexing
• Real-time context augmentation for LLMs

Use cases of Ragdocs

• Enhancing AI responses with relevant documentation
• Building documentation-aware AI assistants
• Creating context-aware tooling for developers
• Implementing semantic documentation search
• Augmenting existing knowledge bases

FAQ from Ragdocs

What are the runtime dependencies?

Ragdocs requires Node.js, a Qdrant vector database (local or cloud), and an embeddings provider – either a local Ollama instance or an OpenAI API key.

How can I deploy Ragdocs locally or in the cloud?

For local development, use the provided Docker Compose file to start Qdrant and Ollama. For production, use a hosted Qdrant Cloud service and set QDRANT_URL and QDRANT_API_KEY.

Which embeddings providers are supported?

Ragdocs supports Ollama (using the nomic-embed-text model) and OpenAI as embeddings providers, configured via the EMBEDDINGS_PROVIDER environment variable.

How do I use Ragdocs with Claude Desktop?

Add a JSON entry under mcpServers in your claude_desktop_config.json, specifying the command, arguments, and environment variables for your chosen provider and Qdrant instance.

What tools does Ragdocs expose?

It provides search_documentation, list_sources, extract_urls, remove_documentation, list_queue, run_queue, and clear_queue for managing and querying documentation.