Kagi Search MCP server

The Kagi MCP server integrates Kagi's powerful search and summarization capabilities with AI assistants through the Model Context Protocol. This allows AI assistants like Claude to access real-time information through Kagi's search API and utilize its summarization tools for websites, PDFs, and videos.

Installation

Before getting started, ensure you have access to the Kagi search API, which is currently in closed beta. Contact [email protected] to request an invite.

Prerequisites

First, install the uv package manager:

For MacOS/Linux:

curl -LsSf https://astral.sh/uv/install.sh | sh

For Windows:

powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

Installing via Smithery

The easiest way to install the Kagi MCP server for Claude Desktop is through Smithery:

npx -y @smithery/cli install kagimcp --client claude

Configuration

Setting Up with Claude Desktop

Add the following to your Claude Desktop configuration:

{
  "mcpServers": {
    "kagi": {
      "command": "uvx",
      "args": ["kagimcp"],
      "env": {
        "KAGI_API_KEY": "YOUR_API_KEY_HERE",
        "KAGI_SUMMARIZER_ENGINE": "YOUR_ENGINE_CHOICE_HERE"
      }
    }
  }
}

You can find your configuration file location by navigating to: Hamburger Menu → File → Settings → Developer → Edit Config.

Usage

Running Queries

Once configured, you can ask Claude questions that require external information:

• For search: "Who was time's 2024 person of the year?"
• For summarization: "summarize this video: https://www.youtube.com/watch?v=jNQXAC9IVRw"

Claude will automatically use the Kagi MCP server to retrieve the information.

Debugging

If you encounter issues, you can use the MCP inspector:

npx @modelcontextprotocol/inspector uvx kagimcp

Advanced Configuration

Environment Variables

You can customize the server behavior using environment variables:

• FASTMCP_LOG_LEVEL: Adjust the logging level (e.g., "ERROR", "INFO")
• KAGI_SUMMARIZER_ENGINE: Choose the summarization engine to use (e.g., "daphne", "cecil")
  • Cecil is used by default if no engine is specified
  • You can learn about the different summarization engines available at the Kagi help documentation

API Key Security

Always keep your Kagi API key secure and never share it publicly. The key should only be set in your environment variables as shown in the configuration examples.

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 "kagi" '{"command":"uvx","args":["kagimcp"],"env":{"KAGI_API_KEY":"YOUR_API_KEY_HERE","KAGI_SUMMARIZER_ENGINE":"cecil"}}'

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": {
        "kagi": {
            "command": "uvx",
            "args": [
                "kagimcp"
            ],
            "env": {
                "KAGI_API_KEY": "YOUR_API_KEY_HERE",
                "KAGI_SUMMARIZER_ENGINE": "cecil"
            }
        }
    }
}

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": {
        "kagi": {
            "command": "uvx",
            "args": [
                "kagimcp"
            ],
            "env": {
                "KAGI_API_KEY": "YOUR_API_KEY_HERE",
                "KAGI_SUMMARIZER_ENGINE": "cecil"
            }
        }
    }
}

3. Restart Claude Desktop for the changes to take effect