Search the web using Kagi's search API
Kagi search mcp server connects Kagi Search to AI assistants that speak the Model Context Protocol. Search the web using Kagi's search API.
An MCP server backed by the Kagi API. It exposes search and extraction tools to MCP-compatible clients.
Once connected, the assistant can call these 5 tools directly:
Search — Who was Time's 2024 person of the year?Extract — extract the full content of https://en.wikipedia.org/wiki/Model_Context_ProtocolSmithery — The Smithery tool exposed by this serverKiro — Add to your Kiro MCP config file (~/.kiro/settings/mcp.json for global, or .kiro/settings/mcp.json for project-scoped) using the same mcpServers JSON asOpenCode — Edit the OpenCode configuration file in ~/.config/opencode/opencode.json and add the following:The 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.
KAGI_API_KEY. - uv for the recommended uvx install path. Install uv: Windows:Knowledge and memory servers address the most frustrating trait of language models — walking into every conversation with no recollection of the last one. Kagi Search sits in that group, and the shape of its toolset — Search, Extract, Smithery among others — tells you what it is really for. Worth comparing against the other knowledge memory 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 |
|---|---|
| Search | Who was Time's 2024 person of the year? |
| Extract | extract the full content of https://en.wikipedia.org/wiki/Model_Context_Protocol |
| Smithery | The Smithery tool exposed by this server. |
| Kiro | Add to your Kiro MCP config file (~/.kiro/settings/mcp.json for global, or .kiro/settings/mcp.json for project-scoped) using the same mcpServers JSON as [Claude Desktop](#claude-desktop). See the [Kiro MCP documentation] |
| OpenCode | Edit the OpenCode configuration file in ~/.config/opencode/opencode.json and add the following: |
{
"mcpServers": {
"kagi": {
"command": "uvx",
"args": ["kagimcp"],
"env": {
"KAGI_API_KEY": "YOUR_API_KEY_HERE"
}
}
}
}Configuration as documented by the project. Restart the client after saving.
KAGI_API_KEY. - uv for the recommended uvx install path. Install uv: Windows:| Variable | Description | Required |
|---|---|---|
| KAGI_API_KEY | Credential the server authenticates with. | Yes |
A knowledge graph your assistant keeps between sessions — entities, relations and observations that persist.
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Your workspace, on speaking terms with AI — search, read and write Notion pages and databases.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Symbol-level code navigation, refactoring and memory for coding agents — the IDE brain your assistant has been missing.
Chat with your second brain — search, read and write vault notes through the Local REST API.