MCP Servers Kagi

🚀 Kagi Server for MCP Server

An MCP server integrated with the Kagi API

This is a TypeScript-based MCP server that integrates the Kagi Search API. It demonstrates its functionality by implementing core MCP concepts:

• A tool for web search and other operations using Kagi
  • It accepts a query string and optional limit parameters
  • Returns search results from the Kagi API

✨ Features

Implemented Tools

• kagi_search - Conduct web searches using Kagi
  • Accepts a query string and optional limit parameters
  • Returns search results from the Kagi API

Planned Tools (Not Yet Implemented)

• kagi_summarize - Generate summaries of web pages or text
• kagi_fastgpt - Obtain quick responses using Kagi's FastGPT
• kagi_enrich - Retrieve rich news results on specific topics

📦 Installation

Install Dependencies

npm install

Build the Server

npm run build

Development with Auto-rebuild

npm run watch

🚀 Quick Start

Environment Configuration

Create a .env file in the project root directory containing your Kagi API key:

KAGI_API_KEY=your_api_key_here

Ensure that you add .env to your .gitignore file for security.

Installation via Smithery

To automatically install the Kagi Server for Claude Desktop via Smithery:

npx @smithery/cli install kagi-server --client claude

To use it with Claude Desktop, add the server configuration:

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

{
  "mcpServers": {
    "kagi-server": {
      "command": "/path/to/kagi-server/build/index.js",
      "env": {
        "KAGI_API_KEY": "your_api_key_here"
      }
    }
  }
}

Debugging

Since MCP servers communicate via standard input/output, debugging can be challenging. We recommend using MCP Inspector, which is available as a package script:

npm run inspector

The Inspector will provide a URL to access browser debugging tools.

💻 Usage Examples

Basic Usage

Once the server is running and connected to Claude Desktop, you can use it for web searches. For example:

1. Ask Claude: "Can you search for the latest developments in quantum computing?"
2. Claude will use the kagi_search tool to obtain results from the Kagi API.
3. Claude will then summarize or analyze the search results.

⚠️ Important Note

The planned tools (summarize, fastgpt, enrich) are not yet implemented and cannot be used.

🤝 Contribution

Contributions are welcome! Please feel free to submit Pull Requests. Some areas where you can contribute include:

• Implementing the planned tools (summarize, fastgpt, enrich)
• Improving error handling and input validation
• Enhancing the quality of documentation and examples

📄 License

This project is released under the MIT License.

📚 Documentation (Roadmap)

• Implement the kagi_summarize tool for web page and text summarization
• Implement the kagi_fastgpt tool to obtain quick responses
• Implement the kagi_enrich tool to retrieve rich news results
• Improve error handling and add more robust input validation
• Add more comprehensive usage examples and documentation
• Publish to npm for easy installation and use with Claude Desktop and npx