Use This MCP server To

Integrate Kagi search results into AI model context Enable real-time search data access for LLMs Enhance AI workflows with Kagi-powered tools Provide structured search API data to AI clients Deploy Kagi MCP server for Claude Desktop integration

README

Kagi MCP server

smithery badge

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 | 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:

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

Setup with 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
      }
    }
  }
}

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 kagimcp

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 | sh

Windows:

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 sync

Setup 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 \
      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: #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

kagimcp FAQ

How do I install the Kagi MCP server?

Install 'uv' first using the provided shell script for MacOS/Linux or PowerShell for Windows, then install Kagi MCP via Smithery or manually.

Is access to the Kagi search API open to everyone?

No, the Kagi search API is currently in closed beta and requires an invite. Contact support@kagi.com to request access.

Can I use Kagi MCP server with clients other than Claude Desktop?

While the README highlights Claude Desktop integration, the server is designed to work with any MCP-compatible client that can consume its structured data.

What platforms does the Kagi MCP server support?

It supports MacOS, Linux, and Windows platforms with installation instructions provided for each.

How does Kagi MCP server enhance AI model capabilities?

By providing real-time, structured search data and tool outputs, it allows LLMs to incorporate fresh, relevant information into their responses.

Is the Kagi MCP server secure?

Yes, it follows MCP principles for secure, scoped, and observable interactions between the model and the server.

Where can I find support or report issues?

You can reach out to Kagi support via support@kagi.com or check the GitHub repository for issue tracking.