Kagi Search MCP Server

The server implements calls of [API methods](https://help.kagi.com/kagi/api/overview.html): - fastgpt - enrich/web - enrich/news

Local serverstdio

What is the Kagi Search MCP MCP server?

Kagi Search MCP MCP server is a locally run integration for AI assistants that speak the Model Context Protocol. The server implements calls of API methods: - fastgpt - enrich/web - enrich/news.

What the assistant can call

Once Kagi Search MCP is connected, these are the calls the assistant has available:

  • Resources — The server implements calls of API methods: - fastgpt - enrich/web - enrich/news
  • Prompts — The Prompts tool exposed by this server
  • Tools — The server implements several tools: - ask_fastgpt to search web and find an answer - enrich_web to enrich model context with web content -
  • Debugging — The Debugging tool exposed by this server

Configuration and credentials

You will need 2 environment variables: KAGI_API_KEY, UV_PUBLISH_TOKEN. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

Setting it up

@smithery/cli on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.

Choosing this one

Among the search and retrieval options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Kagi Search MCP's toolset — Resources, Prompts, Tools and 1 more — is a fair guide to whether it matches your workflow. It is maintained by apridachin; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Before you rely on it

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the kagi search mcp mcp server does with a few real requests.

Available tools

ToolWhat it does
ResourcesThe server implements calls of [API methods](https://help.kagi.com/kagi/api/overview.html): - fastgpt - enrich/web - enrich/news
PromptsThe Prompts tool exposed by this server.
ToolsThe server implements several tools: - ask_fastgpt to search web and find an answer - enrich_web to enrich model context with web content - enrich_news to enrich model context with latest news
DebuggingThe Debugging tool exposed by this server.

How to install the Kagi Search MCP MCP server

{
  "mcpServers": {
    "kagi-search": {
      "command": "npx",
      "args": ["-y", "@smithery/cli"],
      "env": {
        "KAGI_API_KEY": "your-value",
        "UV_PUBLISH_TOKEN": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
KAGI_API_KEYCredential the server authenticates with.Yes
UV_PUBLISH_TOKENCredential the server authenticates with.Yes

Example prompts to try

  • Use Kagi Search MCP to Resources.
  • Use Kagi Search MCP to Prompts.
  • Use Kagi Search MCP to Tools.

Frequently asked questions

It connects Kagi Search MCP to MCP-compatible AI assistants such as Claude and Cursor, exposing 4 tools (Resources, Prompts, Tools, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Kagi Search MCP directly.