WorkerKit Directory

WorkerKit Directory 是一個遠端 MCP 伺服器，位於 https://mcp.workerkit.ai。AI 工作者，隨時可執行。選擇一個套件，連接它所要求的應用程式，它就會在首次執行時，以您的規則開始工作。

文件

Two MCP servers for WorkerKit, served over Streamable HTTP.

Workers management (authenticated)

Manage your AI worker fleet: list workers with live run state, trigger and watch runs, curate memory (rules & facts), manage schedules and instructions, start/stop workers, and install kits from the public directory as new workers.

https://mcp.workerkit.ai/workers

Authentication: connect via OAuth from your MCP client, or send a WorkerKit manager key directly as Authorization: Bearer pe_mgr_…. An account admin mints manager keys under Fleet access.

Kits directory (public, no auth)

Browse and search the public WorkerKit kits directory — pre-built AI workers with pre-scoped app permissions: search by job, app, category or model, inspect a kit's permissions and instruction, and get its install page.

https://mcp.workerkit.ai/directory

Claude Code

claude mcp add --transport http workerkit https://mcp.workerkit.ai/workers
claude mcp add --transport http workerkit-directory https://mcp.workerkit.ai/directory