Skip to main content
PublishBuddy hosts a Model Context Protocol (MCP) server. MCP is the open standard AI assistants use to call tools inside other applications. Connect an MCP client to your workspace and it can list your profiles, read analytics, create and schedule posts, and generate images, videos, and carousels with AI Studio’s models, using the same tools that power the AI Agent inside the dashboard.
Endpoint: https://api.publishbuddy.com/mcp Transport: Streamable HTTP (JSON-RPC over POST) Auth: OAuth 2.1 sign-in (ChatGPT, Claude, and other clients that support it), or Authorization: Bearer <your-token> with an API token that has the mcp ability Plans: Pro and Business

Connect a client

Sign in from ChatGPT or Claude, or paste a token into Claude Code, Cursor, VS Code, Windsurf, and Claude Desktop.

Tool reference

Every tool the server exposes, what it needs, and what it costs in AI credits.

​
What an MCP client can do

Read analytics

Engagement summaries, top and bottom posts, best times to post, and hashtag performance for any profile or the whole workspace.

Draft and schedule

Create draft posts with media from the library, then schedule them for a date and time or add them to a profile’s queue.

Generate media

Generate images, videos, and carousels with AI Studio’s models, quoted in credits before anything is charged. Finished files land in the media library, ready to attach. Rendering carousel slides isn’t working in production at the moment.

Understand what works

Explain why a post performed, search the library by visual features, and build a creative brief from reference posts.

​
How it fits together

  • One sign-in or token, one user. The sign-in or the token identifies you. Every tool runs with the permissions your user has in the dashboard, so a member who can only draft in the app can only draft over MCP too, and sees only the profiles they see there.
  • One workspace per request. A signed-in app works in the workspace you picked when you allowed it. With an API token, requests run against your active workspace, the one you last used in the dashboard; to target a different workspace, send an X-Workspace-Id header with the workspace UUID from GET /workspaces.
  • Same server as the in-app AI Agent. The assistant in the dashboard is an MCP client of this server. Connecting your own client gives it the same tools; it does not add a second set of permissions.
The Copy page menu on these docs also offers an MCP option. That is the docs site’s own search server hosted by Mintlify, not the PublishBuddy workspace server described here.

​
Credits

Most tools are free of AI credits. The ones that call an AI model to produce something are charged against the workspace’s monthly credits, the same pool the in-app AI Agent uses (500 on Pro, 2,500 on Business). A tool that would exceed the remaining balance returns a 402 before it runs, with the cost and the balance in the message. The AI Studio tools answer with a tool error instead, naming the quote, the balance, and a cheaper model when one exists, and charge nothing; quote_media gives the exact figure before the call, and a failed generation is refunded. See Media (AI Studio).

​
Rate limits

The MCP endpoint is limited to 60 requests per minute per user. Exceeding it returns 429 with a Retry-After header. Each tool call is one request; an assistant working through a multi-step task stays well inside this.

​
Errors you may see

​
MCP or the REST API?

Use the REST API when code is doing the work: a pipeline that publishes from your CMS, a nightly analytics sync, or a client portal. Use MCP when a person is doing the work through an assistant: planning a week of content in one conversation, pulling numbers into a report you are already writing, or publishing a changelog post from your editor. Both take the same API tokens and respect the same plan; MCP also takes a sign-in.