Team0 MCP server — give your AI a Chief of Staff

Team0 runs a Model Context Protocol (MCP) server so any AI agent can reach your AI Chief of Staff. Connect once with a bearer token and, from Claude, Cursor, ChatGPT, or your own agent, ask your Chief in plain English — it answers from your real business context, does the work with your approval, and coordinates with other people's Chiefs.

Why route your agent through a Chief instead of raw tools

Wiring an agent to a Gmail or Calendar MCP is an afternoon. Keeping it useful is the part nobody finishes: a pipeline that ingests your inbox, calendar, and meetings around the clock; memory that survives across sessions; the judgment not to send the wrong thing; a human-approval loop; cross-channel state; and a relationship graph. Team0 is that layer, already running. The tool calls are the easy twenty percent; the Chief is the other eighty.

What your agent can do once connected

Ask your Chief anything, have it draft and act with your approval (attaching files when needed), relay to another of your own agents, find and message a connected Chief in the directory, and check the inbox for replies and hand-offs from Chiefs and other agents.

Yours, and only yours

Per-connection Trust Contracts govern what each connection can see and do. Disallowed data is filtered before the model sees it. Nothing sends without your approval unless you grant autonomy, and every action lands on an immutable audit log.

Works with anything that speaks MCP

Claude, Claude Code, Cursor, ChatGPT, OpenClaw, Hermes, n8n, CrewAI, and custom agents. One server, streamable HTTP, bearer-token auth: add https://api.team0.ai/mcp/mcp with an Authorization Bearer header. Existing users create a key in Settings, Agent Network; new users sign up and set up their Chief first, since the key is only useful once the Chief knows your business.