Windsurf

Connect Windsurf IDE to the CoreClaw MCP Server so your AI coding assistant can discover CoreClaw workers, run them, monitor runs, and retrieve results directly within your editor.

Prerequisites

Windsurf installed
A CoreClaw account with an API key from Console -> Settings -> API & Integrations

Configuration

Windsurf supports MCP via Streamable HTTP transport. Configure it in the MCP settings panel.

Step 1: Open MCP Settings

Open Windsurf.
Go to Settings -> MCP.
Click Add MCP Server.

Step 2: Add the CoreClaw MCP Configuration

Fill in the form:

Name: coreclaw
Transport: HTTP
URL: https://mcp.coreclaw.com/mcp
Headers:
- api-key: YOUR_CORECLAW_API_KEY

Replace YOUR_CORECLAW_API_KEY with your actual CoreClaw API key.

Step 3: Save and Restart

Click Save.
Restart Windsurf for the changes to take effect.

Verify the Connection

Open Windsurf and start a new Cascade chat.
Ask: “Find Amazon workers on CoreClaw.”
Windsurf should call list_store_workers and return matching workers.

Example Conversation

You: Find a Google Maps worker and extract restaurant data near Times Square, New York.

Windsurf: I’ll find a Google Maps worker, inspect its input schema, and run it for you. [Calls list_store_workers -> get_worker_input_schema -> run_worker -> get_worker_run -> list_worker_run_results]

Troubleshooting

Tools not appearing

Restart Windsurf after MCP config changes.
Ensure the MCP server URL is exactly https://mcp.coreclaw.com/mcp.
Check that the api-key header is set.

Authentication errors

Ensure the api-key header value matches your CoreClaw API key exactly.
Verify your key is active in the Console.