Skip to main content
The Postsiva Unified MCP lets AI agents call Postsiva tools instead of hand-writing REST requests. Each tool runs the same backend logic as the website/WhatsApp agent.

​
How it works

  1. Your MCP client connects to https://mcp.postsiva.com/mcp with your workspace API key.
  2. The agent calls tools (publish, get_user_posts, …).
  3. Each call resolves workspace_id from the key and invokes the shared LangChain tool layer.
  4. Results are JSON returned to the agent.
There is no separate MCP behavior — quotas, plan gates, and platform rules match the REST API.

​
Endpoint

https://mcp.postsiva.com/mcp
  • Transport: Streamable HTTP (stateless)
  • Auth: X-API-Key: psk_live_… or ?apikey=psk_live_…

​
Who it’s for

  • Cursor / Claude Desktop — manage social from your editor
  • n8n / automation — AI Agent node with MCP
  • Custom agents — any MCP-compatible client
  • Internal tools — same surface as WhatsApp agent, different channel

​
Requirements

  • Pro plan (mcp_enabled)
  • Valid workspace API key
  • Social accounts connected in that workspace

​
Tool count

13 tools — accounts, posting, queue, posts, analytics, comments, AI generation, platform connect/disconnect, web search. See the full Tool catalog.

​
vs REST API

RESTMCP
CallerYour codeAI agent
InterfaceHTTP paths + JSON bodiesNamed tools + arguments
Best forPipelines, CRON, webhooksNatural language workflows
Use REST when you know the exact call; use MCP when an agent should decide which action to take.

​
Next steps

Connect & setup

Cursor, Claude, headers

Tool catalog

All 13 tools

Cursor guide

Postsiva MCP in Cursor

n8n

AI Agent + MCP