The Kagi MCP Server provides access to Kagi's search and summarization tools:
Web Search: Execute one or more search queries, returning numbered results for easy reference.
Content Summarization: Summarize videos or other content using customizable engines like 'cecil' or 'daphne'.
Claude Desktop Integration: Configure and integrate with Claude Desktop for enhanced functionality.
Customization Options: Adjust logging levels via the
FASTMCP_LOG_LEVELenvironment variable.Requirements: Needs a Kagi API key and access to Kagi's closed beta search API.
Integrates with Kagi search API to provide search capabilities to Claude AI, allowing Claude to answer questions requiring up-to-date information through internet search
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Kagi MCP Serverwhat are the latest developments in quantum computing?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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:
curl -LsSf https://astral.sh/uv/install.sh | shWindows:
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:
npx -y @smithery/cli install kagimcp --client claudeSetup with Claude
Claude Desktop
// 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):
claude mcp add kagi -e KAGI_API_KEY="YOUR_API_KEY_HERE" KAGI_SUMMARIZER_ENGINE="YOUR_ENGINE_CHOICE_HERE" -- uvx kagimcpNow 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):
{
"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:
npx @modelcontextprotocol/inspector uvx kagimcpRelated MCP server: Database Tools for Claude AI
Local/Dev Setup Instructions
Clone repo
git clone https://github.com/kagisearch/kagimcp.git
Install dependencies
Install uv first.
MacOS/Linux:
curl -LsSf https://astral.sh/uv/install.sh | shWindows:
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"Then install MCP server dependencies:
cd kagimcp
# Create virtual environment and activate it
uv venv
source .venv/bin/activate # MacOS/Linux
# OR
.venv/Scripts/activate # Windows
# Install dependencies
uv syncSetup with Claude Desktop
Using MCP CLI SDK
# `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
# 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:
# 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 \
kagimcpThen 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_LEVELenvironment 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_ENGINEenvironment variable (e.g.KAGI_SUMMARIZER_ENGINE="daphne")Learn about the different summarization engines here
There may be more secure ways of plugging into the MCP. A user wrote down some details here