mcp-server-weaviate

Mirror of

Catalog onlyCatalog onlySTDIO

Overview

The mcp-server-weaviate is a server designed to work with Weaviate, a vector search engine, enabling users to manage and query their data effectively.

To use the mcp-server-weaviate, ensure you have uv installed, clone the repository, and configure the server with your Weaviate URL and API keys in the provided configuration file.

Integration with Weaviate for vector search capabilities - Customizable server configuration - Support for multiple API keys and collections

Managing and querying large datasets using Weaviate.
Integrating AI capabilities with vector search.
Developing applications that require efficient data retrieval.

Add to your AI client

Use these steps to connect mcp-server-weaviate in Cursor, Claude, VS Code, and other MCP-compatible apps. The same JSON appears in the Use with menu above for one-click copy.

Cursor

Add this to your .cursor/mcp.json file in your project root, then restart Cursor.

.cursor/mcp.json

{
  "mcpServers": {
    "weaviate-mcp-server-weaviate-mcp-mirror": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-weaviate-mcp-server-weaviate-mcp-mirror"
      ]
    }
  }
}

Claude Desktop

Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)

{
  "mcpServers": {
    "weaviate-mcp-server-weaviate-mcp-mirror": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-weaviate-mcp-server-weaviate-mcp-mirror"
      ]
    }
  }
}

Claude Code

Add this to your project's .mcp.json file. Claude Code will detect it automatically.

.mcp.json (project root)

{
  "mcpServers": {
    "weaviate-mcp-server-weaviate-mcp-mirror": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-weaviate-mcp-server-weaviate-mcp-mirror"
      ]
    }
  }
}

VS Code (Copilot)

Add this to your .vscode/mcp.json file. Requires the GitHub Copilot extension with MCP support enabled.

.vscode/mcp.json

{
  "servers": {
    "weaviate-mcp-server-weaviate-mcp-mirror": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-weaviate-mcp-server-weaviate-mcp-mirror"
      ]
    }
  }
}

Windsurf

Add this to your Windsurf MCP config file, then restart Windsurf.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "weaviate-mcp-server-weaviate-mcp-mirror": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-weaviate-mcp-server-weaviate-mcp-mirror"
      ]
    }
  }
}

Cline

Open Cline settings, navigate to MCP Servers, and add this server configuration.

Cline MCP Settings (via UI)

{
  "mcpServers": {
    "weaviate-mcp-server-weaviate-mcp-mirror": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-weaviate-mcp-server-weaviate-mcp-mirror"
      ]
    }
  }
}

FAQ

What is Weaviate?

Weaviate is an open-source vector search engine that allows for semantic search and data management.

Is there a demo available?

Yes, a demo image is provided in the repository to showcase the server's capabilities.

How do I configure the server?

Configuration is done through a JSON file where you specify your Weaviate URL, API keys, and collection names.

Developer tools