@createworker/mcp

MCP (Model Context Protocol) server for CreateWorker. Drive AI workers — create and run tasks, read deliverables, approve actions, manage knowledge, and connect your own apps — directly from Claude Code, Claude Desktop, Cursor, and any other MCP client.

Requires Node 18+ and a CreateWorker API key (create one in your dashboard under Developer).

Use it in Claude Code

Local (npx):

claude mcp add createworker --env CREATEWORKER_API_KEY=cw_live_… -- npx -y @createworker/mcp

Remote (hosted, zero-install):

claude mcp add --transport http createworker https://www.createworker.com/api/mcp \
  --header "Authorization: Bearer cw_live_…"

Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "createworker": {
      "command": "npx",
      "args": ["-y", "@createworker/mcp"],
      "env": { "CREATEWORKER_API_KEY": "cw_live_…" }
    }
  }
}

Cursor

Add to .cursor/mcp.json (same command/args/env shape as above).

Configuration

Env var	Required	Default
CREATEWORKER_API_KEY	yes	—
CREATEWORKER_BASE_URL	no	https://www.createworker.com

Tools

Workers (workers_list, worker_get/create/update/delete) · Tasks (tasks_list, task_get/create/cancel/wait/deliverables) · approval_decide · clarification_answer · deliverable_get · Knowledge (knowledge_list/get/create/delete) · Integrations — connect your own app (connections_list, connection_create_api, connection_create_webhook, connection_delete, bindings_list, binding_create, binding_delete) · webhook_register · account_get, usage_list.

A key's scopes and each worker's autonomy level still bound what actually executes — write actions stay approval-gated unless a worker is set to auto-execute.

Example prompts

• "List my CreateWorker workers, then create a task for the support worker to summarize today's tickets and wait for the result."
• "Connect my site's API (https://api.example.com, bearer token) and bind it to my content worker so it can publish posts."

License

MIT