Weaviate

You run an MCP server that connects to Weaviate to enable conversational access to your Weaviate data. This server acts as a bridge between your MCP client and the Weaviate instance, facilitating queries, indexing, and data retrieval through the MCP protocol.

How to use

Start by ensuring your Weaviate instance is accessible and you have the necessary API key. You will run the Weaviate MCP server as a local process and load it into your MCP client configuration. Your MCP client can then send queries to the Weaviate MCP server to search, retrieve, and index data from your Weaviate data sources. Use the client to initiate conversations or tasks that require data from Weaviate, and rely on the server to translate those requests into Weaviate API calls and return results.

How to install

Prerequisites: ensure you have uv installed.

Clone the MCP server repository to your development environment.

Create or modify your MCP configuration to include the Weaviate MCP server entry as shown in the snippet below.

To start loading the Weaviate MCP server, provide the required Weaviate URL and API keys in your MCP client configuration. The server configuration uses a Python module entry and requires the PYTHONPATH environment variable to point at the MCP server directory.

Because the server runs as a local process, you don’t need a separate HTTP URL. Instead, point your MCP client at the local stdio server configuration and pass the necessary Weaviate connection details.

Configuration and usage example

{
  "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"
      }
    }
  }
}

Additional sections

Security and access control: protect your Weaviate API key and URL. Store sensitive values in a secure configuration store or environment management tool, and avoid embedding keys directly in client configurations.