kagimcp

Local 2025-08-31 23:12:22 0

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.


smithery badge

Kagi Server MCP server

Setup Intructions

Before anything, ensure you have access to the search API. It is currently in closed beta and available upon request. Please reach out to [email protected] 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"

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"
      }
    }
  }
}

Installing via Smithery

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

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

e.g. "Who was time's 2024 person of the year?"

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"
      }
    }
  }
}

Ask Claude a question requiring search

e.g. "Who was time's 2024 person of the year?"

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.

Notes

  • 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
[
  {
    "description": "Perform web search based on one or more queries. 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.",
    "inputSchema": {
      "properties": {
        "queries": {
          "description": "One or more concise, keyword-focused search queries. Include essential context within each query for standalone use.",
          "items": {
            "type": "string"
          },
          "title": "Queries",
          "type": "array"
        }
      },
      "required": [
        "queries"
      ],
      "title": "searchArguments",
      "type": "object"
    },
    "name": "search"
  }
]