Weaviate MCP server

This MCP server for Weaviate enables integration between Claude Desktop and Weaviate vector database, allowing you to store, retrieve, and search through vector embeddings. It serves as a connector that lets Claude interact with your Weaviate collections through the Model Context Protocol.

Prerequisites

Before installing the Weaviate MCP server, you'll need:

• The uv package manager for Python (required for installation)
• Claude Desktop application
• A Weaviate instance with API access
• An OpenAI API key (used for embeddings)

Installing UV

If you don't have uv installed, you can follow the official installation guide.

Installation

You can install the Weaviate MCP server using one of the following methods:

Automatic Installation via Smithery

The simplest way to install is using Smithery:

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

This automatically configures the server for Claude Desktop.

Manual Installation

For manual installation, you'll need to:

1. Clone the repository
2. Configure Claude Desktop to use the server

Configuration

To configure the MCP server with Claude Desktop, you'll need to edit the Claude Desktop configuration file:

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

Add the following to your configuration file:

{
  "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

Replace the placeholder values with your actual credentials:

• PYTHON_PATH: Path to your Python executable
• YOUR_WEAVIATE_URL: URL of your Weaviate instance
• YOUR_WEAVIATE_API_KEY: API key for your Weaviate instance
• YOUR_SEARCH_COLLECTION: Name of the Weaviate collection for searches
• YOUR_STORE_COLLECTION: Name of the Weaviate collection for storage
• YOUR_OPENAI_API_KEY: Your OpenAI API key (for generating embeddings)
• PATH_TO_MCP_SERVER_WEAVIATE_DIRECTORY: Full path to the directory containing the cloned repository

Usage

After installation and configuration, restart Claude Desktop. The MCP server will be available in your Claude interface, allowing you to:

1. Store information in your Weaviate database directly from Claude
2. Search through your Weaviate collections using natural language queries
3. Retrieve and reference stored information during conversations

The server handles the vector embedding creation and similarity searches behind the scenes, providing Claude with seamless access to your vector database.

Troubleshooting

If you encounter issues with the connection:

• Verify your Weaviate URL and API key are correct
• Ensure your OpenAI API key is valid
• Check that the collection names match existing collections in your Weaviate instance
• Confirm that the PYTHONPATH correctly points to the repository directory

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "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"}}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "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"
            }
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json
• Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "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"
            }
        }
    }
}

3. Restart Claude Desktop for the changes to take effect