The AI Search API MCP server exposes search, job, usage, surface, and watch operations as tools for agents. It uses Streamable HTTP at:
The server implements protocol revision 2025-06-18 and is stateless: every request gets a fresh context, with no MCP session persistence between requests.

Authentication

MCP uses the same API keys as the REST API. Send a restricted sk_live_... or sk_test_... key as a Bearer token:
A missing or invalid key returns HTTP 401, includes WWW-Authenticate: Bearer, and uses the standard flat JSON error shape:
401
OAuth is on the roadmap, but is not available today. MCP clients must send an API key.

Setup

Claude Code

Cursor

Add the server to .cursor/mcp.json. Cursor supports direct HTTP transport:

Claude Desktop

Claude Desktop’s configuration is stdio-oriented, so bridge to the remote server with the standard mcp-remote adapter package:
If your Desktop build supports native remote HTTP MCP servers, point it directly at the MCP URL with the same Authorization header instead of using the bridge.
Replace the placeholder with your real sk_live_... or sk_test_... value. Keep the key server-side and out of source control. Anyone who holds it can spend your credits; revoke and replace it immediately if exposed.

Tool catalog

Every tool call proxies through the corresponding REST endpoint with the same authentication, credits, tenancy, and error semantics. The MCP layer only reshapes JSON to use fewer agent tokens; markdown answers are truncated to about 8,000 characters with a note when truncation occurs.

Errors

Tool errors map to the same stable codes, flat error shape, and docs_url values as the REST API. See Error handling for the complete catalog and retry guidance.

For AI agents

Integrate the same API directly over raw HTTP.

Create a search

The request, response, and billing contract behind the search tool.

Watches

Schedule recurring searches exposed through the watch tools.