Kagi MCP
A Node.js implementation of the Kagi Model Context Protocol server that enables Claude AI to search the web and summarize documents, videos, and audio using Kagi's APIs.
Tools
kagi_search_fetch
Fetch web results based on one or more queries using the Kagi Search API. Use for general search and when the user explicitly tells you to 'fetch' results/information. Results are from all queries given. They are numbered continuously, so that a user may be able to refer to a result by a specific number.
kagi_summarizer
Summarize content from a URL using the Kagi Summarizer API. The Summarizer can summarize any document type (text webpage, video, audio, etc.)
README
Kagi MCP (Node.js)
A Node.js implementation of the Kagi Model Context Protocol (MCP) server. This provides a more stable alternative to the official Python implementation, especially when running multiple instances.
Features
- Search web content using Kagi Search API
- Summarize documents, videos, and audio using Kagi Summarizer API
- No port conflicts when running multiple instances
- Full compatibility with Claude Desktop
Prerequisites
- Node.js 18 or higher
- Kagi API key (request from support@kagi.com)
- Note: The Search API is in closed beta. You may need to request access separately.
Installation
Method 1: Using npx (Recommended for Claude Desktop)
No installation needed! Claude Desktop can run the package directly using npx.
Method 2: Install from npm
npm install -g kagi-mcp
Or use it directly with npx:
npx kagi-mcp
Method 3: Install from GitHub directly
npm install -g github:yuki-yano/kagi-mcp
Method 4: Install from source
git clone https://github.com/yuki-yano/kagi-mcp.git
cd kagi-mcp
npm install
npm run build
npm link
Configuration
Environment Variables
KAGI_API_KEY(required): Your Kagi API keyKAGI_SUMMARIZER_ENGINE(optional): Summarization engine - cecil (default), agnes, daphne, or muriel
Claude Desktop Configuration
Add the following to your Claude Desktop config file:
MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Method 1: Using npx (Recommended - No installation required)
{
"mcpServers": {
"kagi": {
"command": "npx",
"args": ["kagi-mcp"],
"env": {
"KAGI_API_KEY": "your-kagi-api-key"
}
}
}
}
This method automatically downloads and runs the latest version from npm without requiring manual installation.
Method 2: Using globally installed package
{
"mcpServers": {
"kagi": {
"command": "kagi-mcp",
"env": {
"KAGI_API_KEY": "your-kagi-api-key"
}
}
}
}
Claude Code Configuration
To use with Claude Code CLI, run the following command:
claude mcp add kagi -s user -e KAGI_API_KEY="your-kagi-api-key" -- npx kagi-mcp
This will:
- Add the Kagi MCP server to your Claude Code configuration
- Set it up at the user level (
-s user) - Configure your API key as an environment variable
- Use npx to automatically download and run the latest version from npm
You can also use the MCP inspector for debugging:
# Method 1: Using npx (requires npm package to be published)
KAGI_API_KEY="your-kagi-api-key" npx @modelcontextprotocol/inspector npx kagi-mcp
# Method 2: Using local installation (more reliable)
npm install -g kagi-mcp
KAGI_API_KEY="your-kagi-api-key" npx @modelcontextprotocol/inspector kagi-mcp
# Method 3: Using source build
KAGI_API_KEY="your-kagi-api-key" npx @modelcontextprotocol/inspector node dist/index.js
Usage
The MCP server provides two tools:
kagi_search_fetch
Search the web using Kagi Search API.
{
"queries": ["array of search queries"]
}
kagi_summarizer
Summarize content from a URL.
{
"url": "https://example.com/article",
"summary_type": "summary" | "takeaway", // optional
"target_language": "EN" // optional
}
Development
# Install dependencies
npm install
# Run in development mode
npm run dev
# Build
npm run build
# Run built version
npm start
Troubleshooting
"Malformed authorization token" error
This error indicates that your API key is invalid or not properly formatted. Make sure:
- You have a valid Kagi API key from support@kagi.com
- The key is correctly set in your environment variable
- You're not adding extra quotes or spaces around the key
"401 Unauthorized" error for Search API
The Search API is in closed beta. You may need to:
- Request access to the Search API separately from support@kagi.com
- Ensure your API key has the necessary permissions
Testing your API key
You can test your API key using the included test script:
KAGI_API_KEY="your-api-key" node test-api.js
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.