Kagi MCP Server

What is Kagi MCP Server about?

Kagi MCP Server connects AI models to Kagi's web‑search and summarizer APIs via the Model Context Protocol. It acts as a bridge that lets tools such as Claude Desktop or Claude Code request live search results or have videos/articles summarized without writing custom HTTP calls.

How to use Kagi MCP Server?

1. Install the UV package manager (required for the Python environment).

   curl -LsSf https://astral.sh/uv/install.sh | sh   # macOS/Linux
   # or PowerShell for Windows
   powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
   

2. Clone the repository and set up the virtual environment:

   git clone https://github.com/kagisearch/kagimcp.git
   cd kagimcp
   uv venv
   source .venv/bin/activate   # Windows: .venv\Scripts\activate
   uv sync
   

3. Configure environment variables – at minimum KAGI_API_KEY. Optionally set KAGI_SUMMARIZER_ENGINE (defaults to cecil).
4. Register the server with Claude Desktop (or Claude Code) using the MCP configuration shown in the README. Example for Claude Desktop:

   {
     "mcpServers": {
       "kagi": {
         "command": "uv",
         "args": ["--directory", "/ABSOLUTE/PATH/TO/kagimcp", "run", "kagimcp"],
         "env": {
           "KAGI_API_KEY": "YOUR_API_KEY_HERE",
           "KAGI_SUMMARIZER_ENGINE": "YOUR_ENGINE_CHOICE_HERE"
         }
       }
     }
   }
   

5. Disable Claude’s built‑in web search if you want only Kagi’s results (add a deny permission for WebSearch).
6. Pose a query that requires a tool, e.g., "Who was Time's 2024 Person of the Year?" or "summarize this video: https://www.youtube.com/watch?v=jNQXAC9IVRw".

Key Features of Kagi MCP Server

• Real‑time web search powered by Kagi’s search API.
• Article and video summarization with selectable engines (cecil, daphne, etc.).
• Simple MCP integration for any Model Context Protocol‑compatible client.
• Configurable logging via FASTMCP_LOG_LEVEL.
• Cross‑platform setup using UV (Python) and optional Smithery shortcut.

Use Cases

• Enhancing AI assistants with up‑to‑date web results.
• Providing concise summaries of long articles or videos for downstream processing.
• Building custom agents that need reliable search without hard‑coding HTTP logic.
• Integrating Kagi’s search capabilities into internal tools, chatbots, or research pipelines.

FAQ

Do I need a Kagi API key? Yes, the server requires a valid Kagi API key. Access is currently in closed beta; request one via support@kagi.com.

Can I change the summarizer model? Set KAGI_SUMMARIZER_ENGINE to the desired engine name (e.g., daphne). If omitted, cecil is used.

What if I want to see debug output? Adjust FASTMCP_LOG_LEVEL (e.g., ERROR, INFO, DEBUG).

Is there a graphical inspector? Run the MCP inspector with:

npx @modelcontextprotocol/inspector uvx kagimcp

and open http://localhost:5173.

Can I run the server without UV? The repository is Python‑centric; UV streamlines dependency management. Using a standard venv + pip install -r requirements.txt is also possible, but the README recommends UV.

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 | 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

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 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):

{
  "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 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: 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