Kagi MCP Server Integration

What does “Kagi” MCP Server do?

The Kagi MCP (Model Context Protocol) Server acts as an official bridge between AI assistants and the Kagi search engine, along with related tools. By implementing the MCP standard, it enables AI clients to securely and efficiently access Kagi’s advanced search capabilities and summarization services. This server empowers developers to build workflows where an AI agent can search the web, retrieve up-to-date information, or summarize complex content (such as videos or articles) in real time. The Kagi MCP Server is especially valuable in contexts where accurate, current, and high-quality web data is required to augment AI reasoning, answering, or automation tasks. Integration is possible with various platforms, streamlining the process of connecting LLMs to rich external knowledge and utility.

List of Prompts

No specific prompt templates are mentioned in the available documentation.

List of Resources

No explicit resources are detailed in the available documentation.

List of Tools

No explicit list of tools is given in the available documentation. However, usage examples suggest at least the following:

• search: Allows the AI to perform web searches using Kagi’s API.
• summarizer: Summarizes content such as YouTube videos or articles.

Use Cases of this MCP Server

• Web Search Augmentation: Enables AI agents to answer queries based on up-to-date web information by leveraging Kagi’s search API.
• Content Summarization: Allows LLMs to summarize lengthy online content such as YouTube videos, making information more digestible.
• Automated Research: Supports programmatic research workflows where the AI autonomously gathers and condenses information from the web.
• Custom Knowledge Retrieval: Integrates Kagi’s high-quality search into specialized developer tools or LLM-based assistants, enhancing their contextual awareness.

How to set it up

Windsurf

No specific setup instructions provided for Windsurf.

Claude

1. Prerequisite: Ensure you have access to the Kagi Search API (closed beta; contact support@kagi.com).
2. Locate Configuration: Find claude_desktop_config.json via Hamburger Menu → File → Settings → Developer → Edit Config.
3. Add MCP Server: Insert the following under mcpServers:

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

4. Save and Restart: Save the file and restart Claude Desktop.
5. Verify Setup: Use a search or summarization query to ensure proper functioning.

Cursor

No specific setup instructions provided for Cursor.

Cline

No specific setup instructions provided for Cline.

Note about securing API keys

Set API keys and sensitive configuration using the "env" field in your MCP server configuration. Example:

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

Replace "YOUR_API_KEY_HERE" with your actual key, and do not hard-code secrets elsewhere.

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "kagi": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “kagi” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Based on the available documentation, Kagi MCP provides a solid integration for search and summarization, but lacks detailed, explicit documentation on resources, prompt templates, and advanced MCP features. Its strength is ease of setup and focus on high-value search/summarize tools. I would rate this MCP server a 6/10 for completeness and developer usability.

MCP Score