About MCP Kagi Search
An MCP server that provides Kagi search through a `kagi_search` tool. It requires a Kagi API token and includes setup, development, testing, and CLI installation instructions.
Key features
- 01Kagi search tool
- 02API token configuration
- 03Development mode
- 04MCP Inspector testing
- 05CLI installation
Use cases
- 01Search the web through Kagi from an MCP client
- 02Test search queries with MCP Inspector
MCP support
The server exposes the `kagi_search` tool to MCP clients. The README describes testing it with MCP Inspector.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEMCP Kagi Search
Setup and Usage
- Install dependencies:
uv sync
source .venv/bin/activate
- Set the Kagi API Token:
export KAGI_API_TOKEN='your_actual_token_here'
- Run MCP server in development mode:
mcp dev src/mcp_kagi_search/server.py
- Test via MCP Inspector:
- Open MCP inspector at
http://localhost:5173. - Run the
kagi_searchtool with a query (e.g., "steve jobs").
- CLI Installation:
uv pip install .
- Verify the CLI:
mcp-kagi-search --help
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.