MCP Ragdocs

🚀 RAG Documentation MCP Server

An implemented MCP server that provides capabilities for retrieving and processing documents and offers tool support through vector search, enabling AI assistants to enhance their responses with relevant document context.

✨ Features

• Vector-based document search and retrieval
• Support for multiple document sources
• Semantic search functionality
• Automated document processing
• Real-time context enhancement for LLM capabilities

🛠️ Tools

search_documentation

Search through the stored documentation using natural language queries. Returns matching excerpts and their context, sorted by relevance.

Input:

• query (string): The text to search for in the documentation. It can be a natural language query, a specific term, or a code snippet.
• limit (number, optional): The maximum number of results to return (1 - 20, default: 5). A larger limit provides more comprehensive results but may increase processing time.

list_sources

List all the document sources currently stored in the system. Returns a comprehensive list, including the URLs, titles, and last update times of all indexed document sources. Use this tool to understand the available documentation for searching or to verify if a specific source has been indexed.

extract_urls

Extract and analyze all URLs from a specified web page. This tool crawls the specified web page, identifies all hyperlinks, and optionally adds them to the processing queue for subsequent processing.

Input:

• url (string): The full URL of the web page to analyze (must include the protocol, e.g., https://). The page must be publicly accessible.
• add_to_queue (boolean, optional): If true, automatically adds the extracted URLs to the processing queue for subsequent indexing. Use with caution on large websites to avoid overloading the queue.

remove_documentation

Permanently remove a specific document source from the system by its URL. This operation will affect future search results.

Input:

• urls (array of strings): A list of URLs to remove from the database. Each URL must exactly match the URL used when it was added.

list_queue

List all the URLs currently waiting in the document processing queue. Displays the pending document sources, which will be processed when run_queue is called. Use this tool to monitor the queue status, verify if URLs were added correctly, or check the processing backlog.

run_queue

Process and index all the URLs currently in the document processing queue. Each URL will be processed sequentially, with appropriate error handling and retry logic. Progress updates will be provided during the processing. Long-running operations will continue until the queue is empty or an unrecoverable error occurs.

clear_queue

Remove all pending URLs from the document processing queue. Use this tool to clear the queue, remove unwanted URLs, or cancel pending tasks. This operation is immediate and permanent - if you need to process these URLs again, you will need to add them back.

💼 Use Cases

The RAG documentation tools are suitable for:

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

⚙️ Configuration

Integration with Claude Desktop

Add the following content to the claude_desktop_config.json file:

{
    "MCP server": {
        "enabled": true,
        "configuration": {
            "type": "RAGDocumentation"
        }
    }
}

💻 Usage Examples

Search Documentation

Input:

• query: "How to configure the RAG documentation tool?"
• limit: 5

Output:

[
    {"content": "Step 1: Install the required dependencies.", "source": "documentation/installation.md"},
    {"content": "Step 2: Configure the environment variables.", "source": "documentation/configuration.md"},
    {"content": "Step 3: Start the service.", "source": "documentation/getting-started.md"}
]

List Sources

Input:

• None

Output:

[
    {"url": "documentation/installation.md", "title": "Installation Guide", "last_updated": "2024-01-01"},
    {"url": "documentation/configuration.md", "title": "Configuration Guide", "last_updated": "2024-01-02"}
]

Extract URLs

Input:

• url: "https://example.com/documentation"
• add_to_queue: true

Output:

{
    "status": "success",
    "message": "URLs have been added to the queue."
}

🌐 Environment Variables

• OPENAI_API_KEY: The API key for OpenAI (required)
• QDRANT_URL: The URL of the Qdrant service (required)
• VECTOR_DB_PATH: The path to the vector database (optional, default: ./vector_db)

This documentation describes the functionality, tools, and configuration of the RAG Documentation MCP Server. By combining these features, you can effectively manage and retrieve document content to support AI applications.