Kagi MCP Server

Integrate Kagi Search and Summarization as Model Context Protocol tools.

View on GitHub

216

Stars

Forks

216

Watchers

Issues

Kagi MCP Server enables easy integration of Kagi's search and summarization capabilities with AI systems via the Model Context Protocol. It facilitates tool-based queries such as searching web results or summarizing content, and offers setup instructions for various platforms including Claude Desktop. Users can install and configure the server through package managers, Smithery, or direct Python environments. The project provides configurable environment variables for API access and summarization engine selection, supporting both local development and production usage.

Key Features

Kagi web search integration

Content summarization engine support

Model Context Protocol (MCP) compliant server

Smithery compatibility for easy installation

Claude Desktop and Claude Code setup instructions

Environment variable configuration for API and engine selection

Support for local and development environments

Debugging utilities via inspector tools

Flexible tool-based querying

Supports disabling conflicting assistant search features

Use Cases

Enabling natural language search in AI assistant platforms

Providing automatic summarization of online content and videos

Enhancing contextual understanding for AI models

Integrating external search and summarization tools in custom AI workflows

Rapid prototyping of AI assistants with search tool capabilities

Local development and testing of model context tools

Replacing or augmenting default assistant search features

Accessible, standardized tool deployment for assistant platforms

Securely handling API credentials for tool integrations

Facilitating research use cases needing external information retrieval

README

Kagi MCP server

Setup Intructions

Before anything, unless you are just using non-search tools, ensure you have access to the search API. It is currently in closed beta and available upon request. Please reach out to support@kagi.com for an invite.

Install uv first.

MacOS/Linux:

bash

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

Windows:

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

Installing via Smithery

Alternatively, you can install Kagi for Claude Desktop via Smithery:

bash

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

Setup with Claude

Claude Desktop

json

// claude_desktop_config.json
// Can find location through:
// Hamburger Menu -> File -> Settings -> Developer -> Edit Config
{
  "mcpServers": {
    "kagi": {
      "command": "uvx",
      "args": ["kagimcp"],
      "env": {
        "KAGI_API_KEY": "YOUR_API_KEY_HERE",
        "KAGI_SUMMARIZER_ENGINE": "YOUR_ENGINE_CHOICE_HERE" // Defaults to "cecil" engine if env var not present
      }
    }
  }
}

Claude Code

Add the Kagi mcp server with the following command (setting summarizer engine optional):

bash

claude mcp add kagi -e KAGI_API_KEY="YOUR_API_KEY_HERE" KAGI_SUMMARIZER_ENGINE="YOUR_ENGINE_CHOICE_HERE" -- uvx kagimcp

Now claude code can use the Kagi mcp server. However, claude code comes with its own web search functionality by default, which may conflict with Kagi. You can disable claude's web search functionality with the following in your claude code settings file (~/.claude/settings.json):

json

{
  "permissions": {
    "deny": [
      "WebSearch"
    ]
  }
}

Pose query that requires use of a tool

e.g. "Who was time's 2024 person of the year?" for search, or "summarize this video: https://www.youtube.com/watch?v=jNQXAC9IVRw" for summarizer.

Debugging

Run:

bash

npx @modelcontextprotocol/inspector uvx kagimcp

Local/Dev Setup Instructions

Clone repo

git clone https://github.com/kagisearch/kagimcp.git

Install dependencies

Install uv first.

MacOS/Linux:

bash

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

Windows:

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

Then install MCP server dependencies:

bash

cd kagimcp

# Create virtual environment and activate it
uv venv

source .venv/bin/activate # MacOS/Linux
# OR
.venv/Scripts/activate # Windows

# Install dependencies
uv sync

Setup with Claude Desktop

Using MCP CLI SDK

bash

# `pip install mcp[cli]` if you haven't
mcp install /ABSOLUTE/PATH/TO/PARENT/FOLDER/kagimcp/src/kagimcp/server.py -v "KAGI_API_KEY=API_KEY_HERE"

Manually

json

# claude_desktop_config.json
# Can find location through:
# Hamburger Menu -> File -> Settings -> Developer -> Edit Config
{
  "mcpServers": {
    "kagi": {
      "command": "uv",
      "args": [
        "--directory",
        "/ABSOLUTE/PATH/TO/PARENT/FOLDER/kagimcp",
        "run",
        "kagimcp"
      ],
      "env": {
        "KAGI_API_KEY": "YOUR_API_KEY_HERE",
        "KAGI_SUMMARIZER_ENGINE": "YOUR_ENGINE_CHOICE_HERE" // Defaults to "cecil" engine if env var not present
      }
    }
  }
}

Pose query that requires use of a tool

e.g. "Who was time's 2024 person of the year?" for search, or "summarize this video: https://www.youtube.com/watch?v=jNQXAC9IVRw" for summarizer.

Debugging

Run:

bash

# If mcp cli installed (`pip install mcp[cli]`)
mcp dev /ABSOLUTE/PATH/TO/PARENT/FOLDER/kagimcp/src/kagimcp/server.py

# If not
npx @modelcontextprotocol/inspector \
      uv \
      --directory /ABSOLUTE/PATH/TO/PARENT/FOLDER/kagimcp \
      run \
      kagimcp

Then access MCP Inspector at http://localhost:5173. You may need to add your Kagi API key in the environment variables in the inspector under KAGI_API_KEY.

Advanced Configuration

Level of logging is adjustable through the FASTMCP_LOG_LEVEL environment variable (e.g. FASTMCP_LOG_LEVEL="ERROR")
- Relevant issue: https://github.com/kagisearch/kagimcp/issues/4
Summarizer engine can be customized using the KAGI_SUMMARIZER_ENGINE environment variable (e.g. KAGI_SUMMARIZER_ENGINE="daphne")
- Learn about the different summarization engines here

Star History

Repository Owner

kagisearch

Organization

Repository Details

Language Python

Default Branch main

Size 43 KB

Contributors 4

License MIT License

MCP Verified Nov 12, 2025

Programming Languages

Python

78.76%

Dockerfile

21.24%

Related MCPs

Discover similar Model Context Protocol servers

tavily-search MCP server

A search server that integrates Tavily API with Model Context Protocol tools.

tavily-search MCP server provides an MCP-compliant server to perform search queries using the Tavily API. It returns search results in text format, including AI responses, URLs, and result titles. The server is designed for easy integration with clients like Claude Desktop or Cursor and supports both local and Docker-based deployment. It facilitates AI workflows by offering search functionality as part of a standardized protocol interface.

⭐ 44
MCP
Tomatio13/mcp-server-tavily

Confluence Communication Server MCP Server

Seamlessly interact with Confluence using standardized MCP tools.

Confluence Communication Server MCP Server is a TypeScript-based implementation that enables seamless interaction with Confluence through the Model Context Protocol. It provides tools for running CQL queries, retrieving, and updating Confluence page content, thus showcasing and adhering to core MCP concepts. The server is compatible with Claude Desktop and supports installation via Smithery, emphasizing ease of integration and automation for Confluence management tasks.

⭐ 13
MCP
KS-GEN-AI/confluence-mcp-server

Brave Search MCP Server

MCP-compliant server providing advanced Brave Search API tools via STDIO and HTTP.

Implements a Model Context Protocol (MCP) server for integrating with the Brave Search API, offering tools for web, local business, image, video, and news searches along with AI-powered summarization. Supports both STDIO and HTTP transports and adheres to established MCP conventions for context management. Provides structured tool schemas and customizable parameters to handle sophisticated search queries and results. Enables advanced filtering, multi-type result aggregation, and seamless integration for AI model workflows.

⭐ 337
MCP
brave/brave-search-mcp-server

OpenAI MCP Server

Bridge between Claude and OpenAI models using the MCP protocol.

OpenAI MCP Server enables direct querying of OpenAI language models from Claude via the Model Context Protocol (MCP). It provides a configurable Python server that exposes OpenAI APIs as MCP endpoints. The server is designed for seamless integration, requiring simple configuration updates and environment variable setup. Automated testing is supported to verify connectivity and response from the OpenAI API.

⭐ 77
MCP
pierrebrunelle/mcp-server-openai

Semgrep MCP Server

A Model Context Protocol server powered by Semgrep for seamless code analysis integration.

Semgrep MCP Server implements the Model Context Protocol (MCP) to enable efficient and standardized communication for code analysis tasks. It facilitates integration with platforms like LM Studio, Cursor, and Visual Studio Code, providing both Docker and Python (PyPI) deployment options. The tool is now maintained in the main Semgrep repository with continued updates, enhancing compatibility and support across developer tools.

⭐ 611
MCP
semgrep/mcp

mcp-local-rag

Local RAG server for web search and context injection using Model Context Protocol.

mcp-local-rag is a local server implementing the Model Context Protocol (MCP) to provide retrieval-augmented generation (RAG) capabilities. It performs live web search, extracts relevant context using Google's MediaPipe Text Embedder, and supplies the information to large language models (LLMs) for enhanced, up-to-date responses. The tool is designed for easy local deployment, requiring no external APIs, and is compatible with multiple MCP clients. Security audits are available, and integration is demonstrated across several LLM platforms.

⭐ 89
MCP
nkapila6/mcp-local-rag

View all Alternatives

Didn't find tool you were looking for?

Search AI Tools

Kagi MCP Server

Key Features

Use Cases

README

Kagi MCP server

Setup Intructions

Installing via Smithery

Setup with Claude

Claude Desktop

Claude Code

Pose query that requires use of a tool

Debugging

Local/Dev Setup Instructions

Clone repo

Install dependencies

Setup with Claude Desktop

Using MCP CLI SDK

Manually

Pose query that requires use of a tool

Debugging

Advanced Configuration

Star History

Repository Owner

Repository Details

Programming Languages

Tags

Related MCPs