MCP Directory
ServersClientsBlog

xASO - App Store Optimization

AI-powered App Store Optimization platform for mobile apps

Go to xASO
MCP Directory

Model Context Protocol Directory

MKSF LTD
Suite 8805 5 Brayford Square
London, E1 0SG

MCP Directory

  • About
  • Blog
  • Documentation
  • Contact

Menu

  • Servers
  • Clients

© 2025 model-context-protocol.com

The Model Context Protocol (MCP) is an open standard for AI model communication.
Powered by Mert KoseogluSoftware Forge
  1. Home
  2. Servers
  3. kagimcp

kagimcp

GitHub

This repository provides the Kagi MCP server, enabling integration with Claude Desktop for search-enhanced conversations. It includes setup instructions using uv, Smithery, and local development environments, requiring a Kagi Search API key.

184
9

Kagi MCP Server

This repository hosts the Kagi MCP (Model Context Protocol) server, designed to integrate Kagi search functionality with applications like Claude Desktop. It allows Claude to answer questions requiring real-time search.

Setup Instructions:

First, request access to the Kagi Search API by contacting [email protected]. Install uv using the provided scripts for MacOS/Linux or Windows. For Claude Desktop integration, configure the claude_desktop_config.json file with the server command, arguments, and your Kagi API key. Alternatively, install via Smithery using npx -y @smithery/cli install kagimcp --client claude. To test, ask Claude a search-related question. Debug using npx @modelcontextprotocol/inspector uvx kagimcp.

Local/Dev Setup:

Clone the repository and install dependencies. Create a virtual environment using uv venv, activate it, and then run uv sync. Configure Claude Desktop either using the MCP CLI SDK or manually by editing claude_desktop_config.json. Debug locally using mcp dev or npx @modelcontextprotocol/inspector. Access the MCP Inspector at http://localhost:5173.

Notes:

Adjust the logging level via the FASTMCP_LOG_LEVEL environment variable.

Repository

KA
kagisearch

kagisearch/kagimcp

Created

December 13, 2024

Updated

March 27, 2025

Language

Python

Category

Search & Knowledge