Post with AutoGen
Register PostLake as one function in AutoGen and any agent in your conversation can publish to every social network — one call, one normalised response it can read and act on. Or connect PostLake's MCP server and skip the registration.
Get started free →No card for the free tier · one API for every network · full MCP access
Prefer no code at all? Connect PostLake's hosted MCP server to your AI assistant (Claude, ChatGPT, Cursor and others) and just ask it to post. It authorizes over OAuth — no key to paste. See the MCP guide.
This is the whole integration — connect your accounts once in the dashboard, then:
from autogen import ConversableAgent, register_function
import requests
def post_to_social(text: str, platforms: list[str]) -> dict:
"""Publish a post to the given social networks via PostLake."""
r = requests.post(
"https://api.postlake.dev/v1/posts",
headers={"Authorization": "Bearer YOUR_API_KEY"},
json={"text": text, "platforms": platforms, "profile": "my-brand"},
)
return r.json()
register_function(
post_to_social,
caller=assistant, # the agent that decides to post
executor=user_proxy, # the agent that runs the call
description="Publish a post to social networks.",
)/v1/posts — the snippet above is all of it.register_function, naming the agent that calls it and the agent that executes it.List the platforms in one request and PostLake posts to all of them, returning a single normalised shape — your code never branches per platform.
PostLake manages each network's developer app and OAuth for you — nothing to register or get reviewed yourself.
Idempotency keys mean a retry never double-posts, and analytics come back normalised so an agent can decide what to post next.
A free tier to start, then usage-based credits — one per post. You only pay for posts that actually publish.
Write one Python function that calls PostLake's /v1/posts endpoint and register it with AutoGen's register_function, naming a caller and an executor agent. The agent can then publish to every network through that single function.
No — one function calling PostLake covers every network, so your agent setup stays small and there's no per-platform code to maintain.
Yes. PostLake is an MCP server, so an MCP-capable AutoGen setup can use its posting tools directly instead of registering a custom function.
Python · Node.js · n8n · Make · Zapier · All guides · Full docs
One API and MCP server for every major network. Free to start.
Get started free →