Agents, API and MCP
Letting an AI agent post for you, and the three things that stop it embarrassing you.
How do I let an AI agent post for me?
The quickest way is from inside the assistant: add xpost there and sign in when it asks — the key is created for you. AI agent in the sidebar has the setup for each one — Claude, ChatGPT, Cursor, Claude Code, Codex, Gemini CLI, GitHub Copilot and more — plus plain REST for your own code. A key you create there is an agent key by default, which is what keeps the rules below in force. Both the hosted MCP connector and the REST API are included in every plan.
The developer docs have the whole thing — a quickstart, all the MCP tools, and the REST reference.
What stops an agent posting something embarrassing?
Three things, and they're the reason xpost exists. Every post an agent makes is emailed to you — before it goes out, or as a receipt the moment it has. In copilot mode it lands in Approvals and waits for you instead. And an agent key can never approve anything, including its own work.
Still stuck? Ask a person.
Email support@xpost.to. If it’s about a post that went wrong, the fastest thing you can send is the link to it from Posts → Needs you — that page already has the platform’s own error text on it.
Building on the API or wiring up an agent? The developer docs go deeper than these pages do.