MCP server for Kagi Search API (beta) integration
If you want an AI assistant working directly with MCP Servers Kagi, the mcp servers kagi mcp server is the bridge. MCP server for Kagi Search API (beta) integration.
This is a TypeScript-based MCP server that integrates the Kagi Search API. It demonstrates core MCP concepts by providing:
Once connected, the assistant can call these 5 tools directly:
kagi_search — Perform web searches using Kagikagi_summarize — Generate summaries of web pages or textkagi_fastgpt — Get quick responses using Kagi's FastGPTkagi_enrich — Fetch enriched news results on specific topicsDebugging — Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the [MCPThe server is distributed via npm as @smithery/cli, so most clients can run it without a manual build step. Add it to your MCP client's configuration and restart the client to pick it up — the copy-paste configs for Claude Desktop, Claude Code and Cursor are on this page.
Before the server will start you need to supply one environment variable: KAGI_API_KEY. Keep credentials in your client's env block or a secrets manager rather than committing them.
Developer-tool servers are usually the first ones people connect, because they turn "help me with this code" into an assistant that can actually read the repo and act on it. MCP Servers Kagi sits in that group, and the shape of its toolset — kagi_search, kagi_summarize, kagi_fastgpt among others — tells you what it is really for. Worth comparing against the other developer tools servers in this directory before you commit to one, since several overlap in scope but differ sharply in setup cost and permissions.
| Tool | What it does |
|---|---|
| kagi_search | Perform web searches using Kagi |
| kagi_summarize | Generate summaries of web pages or text |
| kagi_fastgpt | Get quick responses using Kagi's FastGPT |
| kagi_enrich | Fetch enriched news results on specific topics |
| Debugging | Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the [MCP Inspector](https://github.com/modelcontextprotocol/inspector), which is available as a package script: |
{
"mcpServers": {
"servers-kagi": {
"command": "npx",
"args": ["-y", "@smithery/cli"],
"env": {
"KAGI_API_KEY": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| KAGI_API_KEY | Credential the server authenticates with. | Yes |
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
GitHub's official server — repos, issues, pull requests, Actions and code security, straight from your assistant.
Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.
Local repository surgery — status, diffs, commits, branches and history for any repo on disk.
Timezone sanity for AI — current time anywhere and correct conversions, without the model doing date math.