Unleashing LLMs: Weaviate MCP Server for Seamless AI Integration

The Model Context Protocol (MCP) is revolutionizing how Large Language Models (LLMs) interact with the world. By providing a standardized interface for connecting LLMs to external data sources and tools, MCP empowers developers to build more intelligent and context-aware AI applications. This document introduces the Weaviate MCP Server, a powerful tool that leverages the MCP to seamlessly integrate Weaviate, a leading vector database, with your LLM workflows.

Getting Started

Prerequisites

Before diving in, ensure you have the following:

• uv: A fast and efficient Python package installer. Refer to the official documentation for installation instructions.
• Weaviate Instance: A running Weaviate instance with API key.
• OpenAI API Key: An active OpenAI API key for embedding generation.

Installation

Method 1: Smithery (Automated Installation)

For a streamlined setup with Claude Desktop, use Smithery:

npx -y @smithery/cli install @weaviate/mcp-server-weaviate --client claude

Method 2: Manual Configuration (Claude Desktop)

1. Locate the Configuration File:

   • MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json
   • Windows: %APPDATA%/Claude/claude_desktop_config.json

2. Configure the MCP Server:

   Add the following configuration block to the mcpServers section of your claude_desktop_config.json file. Replace the placeholder values with your actual Weaviate and OpenAI credentials.

   {
     "mcpServers": {
       "mcp-server-weaviate": {
         "command": "PYTHON_PATH",
         "args": [
           "-m",
           "src.server",
           "--weaviate-url",
           "YOUR_WEAVIATE_URL",
           "--weaviate-api-key",
           "YOUR_WEAVIATE_API_KEY",
           "--search-collection-name",
           "YOUR_SEARCH_COLLECTION",
           "--store-collection-name",
           "YOUR_STORE_COLLECTION",
           "--openai-api-key",
           "YOUR_OPENAI_API_KEY"
         ],
         "env": {
           "PYTHONPATH": "PATH_TO_MCP_SERVER_WEAVIATE_DIRECTORY"
         }
       }
     }
   }

   Configuration Parameters:

   • PYTHON_PATH: The path to your Python executable.
   • YOUR_WEAVIATE_URL: The URL of your Weaviate instance.
   • YOUR_WEAVIATE_API_KEY: Your Weaviate API key.
   • YOUR_SEARCH_COLLECTION: The name of the Weaviate collection used for search.
   • YOUR_STORE_COLLECTION: The name of the Weaviate collection used for storing data.
   • YOUR_OPENAI_API_KEY: Your OpenAI API key.
   • PATH_TO_MCP_SERVER_WEAVIATE_DIRECTORY: The absolute path to the cloned mcp-server-weaviate directory.

Visual Example