What is MCP
How the Model Context Protocol lets AI assistants act in Posteady on your behalf.
Model Context Protocol (MCP) is an open standard that lets AI assistants securely connect to external tools and data. Think of it as a universal adapter: instead of copying and pasting between your AI chat and Posteady, you connect Posteady once and then simply ask — "draft and schedule a post for tomorrow morning" — and the assistant does it for you.
How it works
Three pieces work together:
- Your AI client (Claude, ChatGPT, …) — where you chat.
- Posteady's MCP server — exposes Posteady actions (publish, schedule, list) as tools the assistant can call.
- Your Posteady account — where posts are actually published, through your connected Threads/X accounts.
When you connect, you grant access through OAuth — a secure sign-in where you approve what the assistant is allowed to do. The assistant never sees your password, and you can revoke access anytime from Posteady.
Posteady's MCP server
| Endpoint | https://www.posteady.com/api/mcp |
| Transport | HTTP Streamable (stateless) |
| Server | posteady v1.0.0 |
| Auth | OAuth 2.1, scope posteady:full |
| Plan | Creator and above |
The OAuth flow is handled automatically by your client — there's nothing to configure by hand. (Building a custom client? The server publishes standard discovery documents at /.well-known/oauth-authorization-server and /.well-known/oauth-protected-resource — RFC 8414 / 9728.)
Next steps
- What you can do — the actions your assistant gains.
Connect your app
- Connect Claude — the easiest, just a few clicks.
- Connect ChatGPT — via Developer Mode (paid plans).
- Connect Gemini — via the Gemini CLI.
- Connect Grok — via a custom connector at grok.com.
- Connect Perplexity — via a custom remote connector (Pro and above).
- Connect Cursor — add it in
~/.cursor/mcp.json. - Other tools — VS Code and any MCP client.