Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.vectorify.ai/llms.txt

Use this file to discover all available pages before exploring further.

The MCP integration provides a bridge between external AI systems and Vectorify’s internal query processing capabilities. It exposes Vectorify’s search and chat functionality as MCP tools that can be discovered and invoked by MCP-compatible AI assistants. The ask_vectorify tool is the primary MCP interface that allows external systems to query Vectorify. It handles both new conversations and continuation of existing chats.
Vectorify supports the 2025-03-26 version of the Model Context Protocol.

​
Adding Vectorify to VS Code

To add the MCP server to VS Code, include the following configuration in your mcp.json file: 
{
  "inputs": [
    {
      "type": "promptString",
      "id": "vectorify_api_key",
      "description": "Vectorify API Key",
      "password": true
    }
  ],
  "servers": {
    "vectorify": {
	  "type": "http",
      "url": "https://mcp.vectorify.ai",
      "headers": {
        "Api-Key": "${input:vectorify_api_key}"
      }
    },
  }
}

​
Adding Vectorify to Cursor

To add the MCP server to Cursor, include the following configuration in your mcp.json file: 
{
  "mcpServers": {
    "vectorify": {
	  "type": "streamable-http",
      "url": "https://mcp.vectorify.ai",
      "headers": {
        "Api-Key": "your_api_key_here"
      }
    }
  }
}

​
Adding Vectorify to Windsurf

To add the MCP server to Cursor, include the following configuration in your mcp_config.json file: 
{
  "mcpServers": {
    "camelai": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "https://mcp.vectorify.ai",
        "--header",
        "Api-Key: your_api_key_here"
      ]
    }
  }
}
After saving your configuration, press the refresh button in the Plugins section or restart Windsurf to load the new MCP server connection.

​
Adding Vectorify to Claude

To add the MCP server to Claude, include the following configuration in the settings: 
{
  "mcpServers": {
    "vectorify": {
      "type": "http",
      "url": "https://mcp.vectorify.ai",
      "headers": {
        "Api-Key": "your_api_key_here"
      }
    }
  }
}