Cloudflare AutoRAG MCP Server

Cloudflare AutoRAG MCP Server

A Model Context Protocol (MCP) server that provides search capabilities for Cloudflare AutoRAG instances. This server enables AI assistants like Claude to directly search and query your AutoRAG knowledge base using three distinct search methods.

Features

• 🔍 Basic Search - Vector similarity search without query rewriting or answer generation
• ✏️ Rewrite Search - Vector search with AI query rewriting but no answer generation (returns document chunks only)
• 🤖 AI Search - Full AI-powered search with optional AI response and configurable query rewriting
• ⚙️ Configurable Parameters - Support for score_threshold (default: 0.5) and max_num_results (1-50, default: 10)
• 📄 Pagination Support - AI search supports cursor-based pagination for large result sets (v1.2.0+)
• 🏢 Multi-AutoRAG Support - Manage and search across multiple AutoRAG instances (v2.0.0+)
• 🌐 Remote Deployment - Runs on Cloudflare Workers for scalability
• 🔗 MCP Compatible - Works with Claude Desktop and other MCP clients

Tools

autorag_basic_search

Performs a basic vector similarity search in your Cloudflare AutoRAG index without AI query rewriting or answer generation. Returns raw document chunks only.

Parameters:

• query (string, required) - The search query text (max 10,000 characters)
• score_threshold (number, optional) - Minimum similarity score threshold (0.0-1.0, default: 0.5)
• max_num_results (number, optional) - Maximum number of results to return (1-50, default: 10)
• autorag_name (string, optional) - Name of the AutoRAG instance to use (defaults to configured default)

autorag_rewrite_search

Performs a vector search with AI query rewriting but no answer generation. Uses Cloudflare's search() method with configurable rewrite_query for better semantic matching and returns only document chunks.

Parameters:

• query (string, required) - The search query text (max 10,000 characters)
• score_threshold (number, optional) - Minimum similarity score threshold (0.0-1.0, default: 0.5)
• max_num_results (number, optional) - Maximum number of results to return (1-50, default: 10)
• rewrite_query (boolean, optional) - Whether to rewrite query for better matching (default: true)
• autorag_name (string, optional) - Name of the AutoRAG instance to use (defaults to configured default)

autorag_ai_search

Performs AI-powered search using Cloudflare's aiSearch() method with optional AI-generated response. Returns document chunks and optionally an AI answer based on the include_ai_response parameter. Supports pagination for large result sets.

Parameters:

• query (string, required) - The search query text (max 10,000 characters)
• score_threshold (number, optional) - Minimum similarity score threshold (0.0-1.0, default: 0.5)
• max_num_results (number, optional) - Maximum number of results to return (1-50, default: 10)
• rewrite_query (boolean, optional) - Whether to rewrite the query for better semantic matching (default: true)
• include_ai_response (boolean, optional) - Whether to include the AI-generated response in the output (default: false)
• cursor (string, optional) - Pagination cursor from previous response to fetch next page of results (v1.2.0+)
• autorag_name (string, optional) - Name of the AutoRAG instance to use (defaults to configured default)

Response includes:

• data - Array of source document chunks with scores and metadata (always included)
• response - AI-generated answer based on retrieved documents (only when include_ai_response: true)
• has_more - Boolean indicating if more results are available
• next_page - Cursor token for fetching the next page (when has_more is true)
• nextCursor - MCP-compliant cursor field (mirrors next_page value)

list_autorags (v2.0.0+)

Lists all available AutoRAG instances configured in the server.

Parameters: None

Response includes:

• autorags - Array of AutoRAG instances with name, description, and is_default flag
• total - Total number of configured AutoRAG instances
• default - Name of the default AutoRAG instance

get_current_autorag (v2.0.0+)

Gets information about the currently configured default AutoRAG instance.

Parameters: None

Response includes:

• current_autorag - Name of the current default AutoRAG instance
• description - Description of the instance
• is_default - Always true for this endpoint

Prerequisites

1. Cloudflare Account with AutoRAG access
2. AutoRAG Instance - Created and indexed in your Cloudflare account
3. Wrangler CLI - For deployment (npm install --save-dev wrangler)

Deployment

1. Clone the repository:
   git clone <repository-url> cd cf-autorag-mcp
2. Install dependencies:
   npm install
3. Configure your AutoRAG instance: Edit wrangler.toml and update the configuration:For a single AutoRAG instance:
   [vars] AUTORAG_NAME = "your-autorag-instance-name"
   For multiple AutoRAG instances:
   [vars] AUTORAG_INSTANCES = "instance1,instance2,instance3" AUTORAG_DESCRIPTIONS = "Description 1,Description 2,Description 3"
4. Deploy to Cloudflare Workers:
   npx wrangler deploy
   This will output your Worker URL, which you'll need for the MCP client configuration.

Claude Desktop Configuration

To use this MCP server with Claude Desktop, add the following configuration to your Claude Desktop config file:

macOS

Edit ~/Library/Application Support/Claude/claude_desktop_config.json:

Windows

Edit %APPDATA%/Claude/claude_desktop_config.json:

Configuration

Replace https://your-worker-url.workers.dev/ with your actual deployed Worker URL.

After updating the configuration:

1. Restart Claude Desktop
2. You should see the AutoRAG search tools available in your conversation

Configuration

Environment Variables

The server uses the following Cloudflare Worker bindings:

• AI - Cloudflare AI binding for AutoRAG access (handles all AutoRAG operations)
• AUTORAG_NAME - Your AutoRAG instance name (for single instance configuration)
• AUTORAG_INSTANCES - Comma-separated list of AutoRAG instances (for multi-instance configuration)
• AUTORAG_DESCRIPTIONS - Comma-separated list of descriptions for each instance

Wrangler Configuration

The wrangler.toml file includes:

Note: The VECTORIZE binding is not required. AutoRAG manages its own vector index access internally through the AI binding.

Usage Examples

Once configured with Claude Desktop, you can use the tools like this:

Basic Search (no query rewriting, no AI response):

Rewrite Search (AI query rewriting, no AI response):

AI Search with Document Chunks Only (default behavior):

AI Search with AI-Generated Response:

Multi-AutoRAG Usage (v2.0.0+):

Important Notes:

• autorag_basic_search performs pure vector search without any AI enhancements
• autorag_rewrite_search uses AI query rewriting but returns document chunks only
• autorag_ai_search by default returns document chunks only (letting the client LLM generate responses), but can optionally include Cloudflare's AI-generated response
• All tools use a default score threshold of 0.5 if not specified
• All tools support the same parameter structure for consistent usage
• Metadata filtering is not supported in Workers bindings - use the REST API if you need filtered queries

Development

Local Development

Project Structure

Technical Details

• Protocol: JSON-RPC 2.0 over HTTP
• Runtime: Cloudflare Workers with Node.js compatibility
• MCP Version: 2024-11-05
• Transport: HTTP-based (no streaming)
• Default Score Threshold: 0.5 for all search tools
• Parameter Validation: Comprehensive validation with clear error messages

Troubleshooting

Common Issues

1. "AutoRAG instance not found"
   • Verify your AUTORAG_NAME in wrangler.toml
   • Ensure your AutoRAG instance is properly created and indexed
2. "MCP server disconnected"
   • Check that your Worker URL is correct in the Claude Desktop config
   • Verify the Worker is deployed and accessible
3. "Tool not found" errors
   • Restart Claude Desktop after configuration changes
   • Check the Worker logs: npx wrangler tail
4. Empty search results
   • Try lowering the score_threshold parameter (default is 0.5)
   • Verify your AutoRAG index has been populated with documents
   • Check that your query terms exist in the indexed content

Logs

View real-time logs from your deployed Worker:

Version History

• v2.0.0 - Multi-AutoRAG support, enhanced schema documentation, removed VECTORIZE binding
• v1.2.0 - Added cursor-based pagination support for AI search tool
• v1.1.3 - Removed filters parameter (not supported in Workers bindings), added helpful error messages for filter attempts
• v1.1.2 - Attempted to fix filter format (discovered Workers bindings don't support filters)
• v1.1.1 - Added include_ai_response parameter to AI search tool, default score threshold of 0.5, comprehensive parameter validation
• v1.1.0 - Added three distinct search tools with boolean parameter support
• v1.0.0 - Initial release

License

This project is licensed under the MIT License.

Contributing

1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Test thoroughly
5. Submit a pull request

Support

For issues related to:

• Cloudflare AutoRAG: Cloudflare AutoRAG Documentation
• Model Context Protocol: MCP Documentation
• This Server: Open an issue in this repository