
Postiz MCP
from IndustryLensOp
Streamline your social media with Postiz. Schedule posts, analyze performance, and manage all accounts in one place
Introduction
Connect AI agents to Postiz using the Model Context Protocol (MCP)
MCP (Model Context Protocol) lets AI agents interact with Postiz directly β listing integrations, scheduling posts, generating images and videos β all through a standardized tool-calling interface.
This means you can connect Claude, ChatGPT, Cursor, or any MCP-compatible client to your Postiz account and manage your social media through natural language.
How It Works
Postiz exposes an MCP server that provides 9 tools to AI agents. The agent discovers these tools, understands their schemas, and calls them on your behalf.
sequenceDiagram
participant Agent as AI Agent
participant MCP as Postiz MCP Server
participant Postiz as Postiz Backend
Agent->>MCP: Connect with API key / OAuth token
MCP-->>Agent: List available tools
Agent->>MCP: Call tool (e.g., schedule post)
MCP->>Postiz: Execute action
Postiz-->>MCP: Return result
MCP-->>Agent: Tool response
Available Tools
Tool Description
integrationList List all connected social media accounts (optionally filtered by group)
groupList List all groups (customers) for your organization
integrationSchema Get platform-specific posting rules and settings schema
triggerTool Execute platform-specific helpers (e.g., list Discord channels)
schedulePostTool Schedule, draft, or immediately publish posts
generateImageTool Generate AI images for posts
generateVideoOptions List available video generation options
videoFunctionTool Get video generator settings (e.g., available voices)
generateVideoTool Generate videos for posts
Authentication
There are two ways to authenticate with the MCP server:
API Key
Get your API key from Settings > Developers > Public API in Postiz. Use it directly in the MCP endpoint URL or as a Bearer token.
OAuth Token
If you're building an app for other Postiz users, use OAuth2 to obtain tokens. OAuth tokens start with pos_ and work the same way as API keys.
Connecting
Use the /mcp endpoint with your API key or OAuth token as a Bearer token:
URL: https://api.postiz.com/mcp Authorization: Bearer your-api-key
This method supports both API keys and OAuth tokens (prefixed with `pos_`).
Use the /mcp/:apiKey endpoint with your API key embedded in the URL:
URL: https://api.postiz.com/mcp/your-api-key
For self-hosted instances, replace https://api.postiz.com with your NEXT_PUBLIC_BACKEND_URL.
Quick Example
Here's what a typical interaction looks like when an AI agent uses Postiz MCP:
-
Agent calls
integrationListβ gets back your connected accounts (X, LinkedIn, etc.) -
Agent calls
integrationSchemawithplatform: "x"β learns X's character limits, settings, and rules -
Agent calls
schedulePostToolβ schedules your post with the correct format
All of this happens automatically when you tell your AI agent something like:
"Schedule a post to X for tomorrow at 10am: Excited to announce our new feature!"
This tool doesn't publish a standard install command β the repository README on GitHub covers its setup.
FAQ
Do I need an OpenAI key to use Postiz MCP?
No. The MCP server just exposes Postiz's tools β your AI client (Claude, ChatGPT, Cursor, etc.) provides the model. Postiz only needs an OPENAI_API_KEY if you use Postiz's own AI features (image generation, copilot) which are separate from the MCP tools surfaced to your client.
What happens when my API key expires or is rotated?
Postiz API keys don't auto-rotate, but if you regenerate one in Settings β Developers β Public API, every MCP client using the old key stops working until you update its config. Update the URL or the Authorization header in your client config and reconnect.
Self-hosted: how do I expose the MCP endpoint?
The MCP server starts as part of the Postiz backend and is reachable at /mcp (Bearer auth), /mcp/:apiKey (key in URL), and /mcp-oauth (OAuth-protected). Your reverse proxy must forward these paths to the backend and support streaming HTTP (Transfer-Encoding: chunked). See Reverse Proxies .
Can MCP read or reply to comments?
Not today. The current tool set is read-only on integrations and write-only on posts/media β there's no getComments or replyToComment exposed via MCP. Comment replies must be triggered through the Postiz UI.