R

RAG Documentation Search

Provides semantic document search and retrieval through vector embeddings, enabling context-aware re...

373 views
0 installs
Updated Nov 22, 2025
Not audited
Provides semantic document search and retrieval through vector embeddings, enabling context-aware responses backed by specific documentation sources
  1. Determine Your Embeddings Provider

    • Choose whether you want to use OpenAI or Ollama for embeddings:
      • For OpenAI, you will need an OpenAI API key.
      • For Ollama, you need a running Ollama server (local or remote).
  2. Collect Required Environment Variable Values

    • All configurations require:

      • QDRANT_URL: The full URL of your Qdrant instance (e.g., http://localhost:6333 for local, or your Qdrant Cloud cluster URL for cloud use).
      • QDRANT_API_KEY: (Only required for Qdrant Cloud) Get this from your Qdrant Cloud console.
      • EMBEDDINGS_PROVIDER: Set to "openai" or "ollama" depending on your setup.
    • If using OpenAI:

    • If using Ollama:

      • OLLAMA_BASE_URL: (Optional, defaults to http://localhost:11434) The URL where Ollama is running.
  3. Obtain a Qdrant API Key (for Qdrant Cloud)

    • Go to the Qdrant Cloud Console
    • Log in or create an account.
    • Create or select a cluster.
    • Navigate to the API Keys section (often under "Settings" or "Access").
    • Generate a new API key.
    • Copy the API key (you’ll need it for QDRANT_API_KEY).
  4. Obtain an OpenAI API Key (if using OpenAI)

    • Visit OpenAI API Keys.
    • Log in.
    • Click Create new secret key.
    • Copy the key to use as OPENAI_API_KEY.
  5. Start Ollama Server (if using Ollama)

    • Install Ollama, if not already installed:
      curl -fsSL https://ollama.com/install.sh | sh
      
    • Start the Ollama server:
      ollama serve
      
    • By default, it will run at http://localhost:11434.
  6. Fill In the FastMCP Connection Interface

    • Go to your FastMCP connection interface.
    • Press the “Install Now” button for MCP-server-ragdocs.
    • In the environment/key input fields, enter the values you obtained for:
      • QDRANT_URL
      • QDRANT_API_KEY (if using Qdrant Cloud)
      • EMBEDDINGS_PROVIDER
      • OPENAI_API_KEY (if using OpenAI)
      • OLLAMA_BASE_URL (if using Ollama)
  7. Save and Apply the Configuration

    • Click “Save” or “Apply” in FastMCP to finalize the setup.

You’re now ready to use MCP-server-ragdocs!

Quick Start

View on GitHub

More for AI and Machine Learning

View All →

More for Developer Tools

View All →

Similar MCP Servers

Report Issue

Thank you! Your issue report has been submitted successfully.