How to integrate Facebook MCP with Autogen

Connect Autogen to Facebook MCP. Post new product launch on our page, upload latest event photos to album, and more using natural language, with authentication handled for you.

Facebook logoFacebook
Oauth2

Facebook is a social media and advertising platform for businesses and creators. It helps you connect, share, and manage content across your public Facebook Pages.

72 Tools

Introduction

This guide walks you through connecting Facebook to AutoGen using the Composio tool router. By the end, you'll have a working Facebook agent that can create and schedule Page posts, reply to comments, send Messenger messages, review Page and post insights, and list ad campaigns through natural language commands.

This guide will help you understand how to give your AutoGen agent real control over a Facebook account through Composio's Facebook MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

For exact tool slugs and parameter tables, see the tool catalog in the Composio docs.

Also integrate Facebook with

TL;DR

Here's what you'll learn:
  • Get and set up your OpenAI and Composio API keys
  • Install the required dependencies for Autogen and Composio
  • Initialize Composio and create a Tool Router session for Facebook
  • Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
  • Configure an Autogen AssistantAgent that can call Facebook tools
  • Run a live chat loop where you ask the agent to perform Facebook operations

What is AutoGen?

Autogen is a framework for building multi-agent conversational AI systems from Microsoft. It enables you to create agents that can collaborate, use tools, and maintain complex workflows.

Key features include:

  • Multi-Agent Systems: Build collaborative agent workflows
  • MCP Workbench: Native support for Model Context Protocol tools
  • Streaming HTTP: Connect to external services through streamable HTTP
  • AssistantAgent: Pre-built agent class for tool-using assistants

What is the Facebook MCP server, and what's possible with it?

The Facebook MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Facebook Page account. It provides structured and secure access to your Facebook Pages, so your agent can perform actions like publishing posts, managing comments, uploading media, and handling page roles on your behalf.

  • Automated content publishing: Have your agent create new posts, photo posts, or video posts directly to your Facebook Page, keeping your audience engaged without manual effort.
  • Media management: Effortlessly upload photos to existing albums or create new albums for organized visual storytelling on your Page.
  • Interactive engagement: Let your agent add reactions, post comments, or reply to comments, fostering genuine interaction with your followers.
  • Page moderation and cleanup: Ask your agent to delete unwanted comments or posts, helping you keep your Facebook Page professional and on-brand.
  • Page team management: Assign tasks or roles to users for your Facebook Page, streamlining collaboration and access control.

What is the Composio tool router, and how does it fit here?

What is Composio SDK?

Composio's Composio SDK helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Composio SDK

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Composio SDK works

The Composio SDK follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Step by step08 STEPS
1

Prerequisites

You will need:

  • A Composio API key
  • An OpenAI API key (used by Autogen's OpenAIChatCompletionClient)
  • A Facebook account you can connect to Composio
  • Some basic familiarity with Autogen and Python async
2

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
  • Keep the API key safe.
Composio API Key
  • Log in to the Composio dashboard.
  • Navigate to your API settings and generate a new API key.
  • Store this key securely as you'll need it for authentication.
3

Install dependencies

bash
pip install composio python-dotenv
pip install autogen-agentchat autogen-ext-openai autogen-ext-tools

Install Composio, Autogen extensions, and dotenv.

What's happening:

  • composio connects your agent to Facebook via MCP
  • autogen-agentchat provides the AssistantAgent class
  • autogen-ext-openai provides the OpenAI model client
  • autogen-ext-tools provides MCP workbench support

4

Set up environment variables

bash
COMPOSIO_API_KEY=your-composio-api-key
OPENAI_API_KEY=your-openai-api-key
USER_ID=your-user-identifier@example.com

Create a .env file in your project folder.

What's happening:

  • COMPOSIO_API_KEY is required to talk to Composio
  • OPENAI_API_KEY is used by Autogen's OpenAI client
  • USER_ID is how Composio identifies which user's Facebook connections to use
5

Import dependencies and create Tool Router session

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio

from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams

load_dotenv()

async def main():
    # Initialize Composio and create a Facebook session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["facebook"]
    )
    url = session.mcp.url
What's happening:
  • load_dotenv() reads your .env file
  • Composio(api_key=...) initializes the SDK
  • create(...) creates a Tool Router session that exposes Facebook tools
  • session.mcp.url is the MCP endpoint that Autogen will connect to
6

Configure MCP parameters for Autogen

python
# Configure MCP server parameters for Streamable HTTP
server_params = StreamableHttpServerParams(
    url=url,
    timeout=30.0,
    sse_read_timeout=300.0,
    terminate_on_close=True,
    headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
)

Autogen expects parameters describing how to talk to the MCP server. That is what StreamableHttpServerParams is for.

What's happening:

  • url points to the Tool Router MCP endpoint from Composio
  • timeout is the HTTP timeout for requests
  • sse_read_timeout controls how long to wait when streaming responses
  • terminate_on_close=True cleans up the MCP server process when the workbench is closed
7

Create the model client and agent

python
# Create model client
model_client = OpenAIChatCompletionClient(
    model="gpt-5",
    api_key=os.getenv("OPENAI_API_KEY")
)

# Use McpWorkbench as context manager
async with McpWorkbench(server_params) as workbench:
    # Create Facebook assistant agent with MCP tools
    agent = AssistantAgent(
        name="facebook_assistant",
        description="An AI assistant that helps with Facebook operations.",
        model_client=model_client,
        workbench=workbench,
        model_client_stream=True,
        max_tool_iterations=10
    )

What's happening:

  • OpenAIChatCompletionClient wraps the OpenAI model for Autogen
  • McpWorkbench connects the agent to the MCP tools
  • AssistantAgent is configured with the Facebook tools from the workbench
8

Run the interactive chat loop

python
print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
print("Ask any Facebook related question or task to the agent.\n")

# Conversation loop
while True:
    user_input = input("You: ").strip()

    if user_input.lower() in ["exit", "quit", "bye"]:
        print("\nGoodbye!")
        break

    if not user_input:
        continue

    print("\nAgent is thinking...\n")

    # Run the agent with streaming
    try:
        response_text = ""
        async for message in agent.run_stream(task=user_input):
            if hasattr(message, "content") and message.content:
                response_text = message.content

        # Print the final response
        if response_text:
            print(f"Agent: {response_text}\n")
        else:
            print("Agent: I encountered an issue processing your request.\n")

    except Exception as e:
        print(f"Agent: Sorry, I encountered an error: {str(e)}\n")
What's happening:
  • The script prompts you in a loop with You:
  • Autogen passes your input to the model, which decides which Facebook tools to call via MCP
  • agent.run_stream(...) yields streaming messages as the agent thinks and calls tools
  • Typing exit, quit, or bye ends the loop

Complete Code

Here's the complete code to get you started with Facebook and AutoGen:

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio

from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams

load_dotenv()

async def main():
    # Initialize Composio and create a Facebook session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["facebook"]
    )
    url = session.mcp.url

    # Configure MCP server parameters for Streamable HTTP
    server_params = StreamableHttpServerParams(
        url=url,
        timeout=30.0,
        sse_read_timeout=300.0,
        terminate_on_close=True,
        headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
    )

    # Create model client
    model_client = OpenAIChatCompletionClient(
        model="gpt-5",
        api_key=os.getenv("OPENAI_API_KEY")
    )

    # Use McpWorkbench as context manager
    async with McpWorkbench(server_params) as workbench:
        # Create Facebook assistant agent with MCP tools
        agent = AssistantAgent(
            name="facebook_assistant",
            description="An AI assistant that helps with Facebook operations.",
            model_client=model_client,
            workbench=workbench,
            model_client_stream=True,
            max_tool_iterations=10
        )

        print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
        print("Ask any Facebook related question or task to the agent.\n")

        # Conversation loop
        while True:
            user_input = input("You: ").strip()

            if user_input.lower() in ['exit', 'quit', 'bye']:
                print("\nGoodbye!")
                break

            if not user_input:
                continue

            print("\nAgent is thinking...\n")

            # Run the agent with streaming
            try:
                response_text = ""
                async for message in agent.run_stream(task=user_input):
                    if hasattr(message, 'content') and message.content:
                        response_text = message.content

                # Print the final response
                if response_text:
                    print(f"Agent: {response_text}\n")
                else:
                    print("Agent: I encountered an issue processing your request.\n")

            except Exception as e:
                print(f"Agent: Sorry, I encountered an error: {str(e)}\n")

if __name__ == "__main__":
    asyncio.run(main())

Conclusion

You now have an Autogen assistant wired into Facebook through Composio's Tool Router and MCP. From here you can:
  • Add more toolkits to the toolkits list, for example notion or hubspot
  • Refine the agent description to point it at specific workflows
  • Wrap this script behind a UI, Slack bot, or internal tool
Once the pattern is clear for Facebook, you can reuse the same structure for other MCP-enabled apps with minimal code changes.
TOOLS

Supported Tools

Every Facebook action and event your agent gets out of the box.

Assign Page Task

Assigns tasks/roles to a business-scoped user or system user for a specific Facebook Page.

Create Comment

Creates a comment on a Facebook post or replies to an existing comment.

Create Multi-Photo Post

Publish one Facebook Page feed post containing one or more photos from public URLs.

Create Photo Post

Creates a photo post on a Facebook Page using an image URL or uploaded image, with an optional caption.

Create Post

Creates a text or link post on a Facebook Page, with a required message field and optional link, scheduling, and targeting.

Create Video Post

Creates a video post on a Facebook Page.

Delete Comment

Deletes a Facebook comment.

Delete Post

Permanently deletes a Facebook Page post.

Get Ad Insights

Read Marketing API performance insights for an advertising object.

Get Comment

Retrieves details of a specific Facebook comment.

Get Comments

Retrieves comments from a Facebook post or comment (for replies).

Get Conversation Messages

Retrieves messages from a specific conversation.

Get Current User

Validates the access token and retrieves the authenticated user's own profile via /me.

Get Graph Object

Read caller-selected fields from an identified Facebook Graph node using permissions already granted to the connection.

Get Graph Objects

Read caller-selected fields from multiple Facebook Graph nodes in one batch request and return successes and failures keyed by requested object ID.

Get Message Details

Retrieves details of a specific message sent or received by the Page.

Get Page Conversations

Retrieves a list of conversations between users and the Page.

Get Page Details

Fetches details about a specific Facebook Page.

Get Page Insights

Retrieves analytics and insights for a Facebook Page, including follower, media view and engagement metrics.

Get Page Photos

Retrieves photos from a Facebook Page.

Get Page Posts

Retrieves posts from a Facebook Page's feed using Graph API v26.

Get Page Roles

Retrieves a list of people and their tasks/roles on a Facebook Page.

Get Page Tagged Posts

Retrieves posts where a Facebook Page is tagged or mentioned.

Get Page Videos

Retrieves videos from a Facebook Page.

Get Post

Retrieves details of a specific Facebook post using a full numeric Page ID and post ID separated by an underscore.

Get Post Insights

Retrieves media-view and unique media-viewer insights for a Facebook post.

Get Post Reactions

Retrieves reactions (like, love, wow, etc.

Get Scheduled Posts

Retrieves one page of scheduled and unpublished posts for a Facebook Page, with pagination information when returned.

Add Reaction

Adds a LIKE reaction to a Facebook post or comment.

List Ad Account Campaigns

List campaigns belonging to a Facebook ad account.

List Ad Accounts

List ad accounts available to the authenticated Facebook user.

List Ads

List ads associated with a Facebook advertising parent.

List Assigned Ad Accounts

Lists ad accounts assigned to a business-scoped user.

List Business Ad Accounts

Lists client ad accounts a Facebook Business can access.

List Businesses

List Business Manager businesses accessible to the connected Facebook user, including selected business details and permitted roles.

List Client Pages

List client-owned Pages accessible to a Business Manager business.

List Managed Pages

Retrieves Facebook Pages managed by a user, with page details, access tokens and tasks when returned.

List Object Attachments

List one page of attachments belonging to a Facebook Graph object.

List Owned Ad Accounts

List ad accounts owned by a Business Manager business, with optional Meta account filtering and cursor pagination.

List Owned Pages

List Facebook Pages owned by a Business Manager business.

List Page Ads Posts

List ad-created Page posts, including optional inline-created and dynamic-ad filters.

List Page Albums

List photo albums belonging to a managed Facebook Page with selected fields and safe cursor pagination.

List Page-Authored Posts

List posts authored by a Facebook Page, excluding visitor and tagged feed content.

List Page Events

List events associated with a managed Facebook Page.

List Page Leadgen Forms

List lead-generation forms owned by a managed Facebook Page.

List Page Reels

List a Facebook Page's Reel video records with selected fields and cursor pagination.

List Page Stories

Lists photo and video stories for a Facebook Page managed by the connected account.

List Page Subscribed Apps

List applications subscribed to webhook notifications for a Facebook Page managed by the connected account.

List Permissions

List granted, declined, or expired Facebook permissions for the connected user and app.

List Published Page Posts

List posts published by a Facebook Page, excluding unpublished posts.

List Video Captions

List one page of caption tracks attached to a managed Page's video.

List Video Tags

Return one page of people or Pages tagged on a Facebook video.

List Video Thumbnails

List available thumbnail images for a Facebook video.

Mark Message Seen

Marks a user's message as seen by the Page, visibly updating the read status in the user's conversation.

Publish Page Photo Story

Publish an existing unpublished Facebook Page photo as a Page Story.

Publish Page Reel

Create a Facebook Page Reel from a hosted or local video and finish it as a draft, scheduled Reel, or publicly published Reel according to video_state.

Publish Scheduled Post

Publishes a previously scheduled or unpublished Facebook post immediately.

Refresh URL Scrape

Ask Facebook to rescrape a public HTTP or HTTPS URL, optionally returning requested URL metadata fields.

Remove Page Task

Removes a user's tasks/access from a specific Facebook Page.

Reschedule Post

Changes the scheduled publish time of an unpublished Facebook post.

Search Ad Targeting Options

Searches query-driven Meta ad targeting option families, including geographic areas, interests, locales, schools, majors, employers, and job titles.

Search Geographic Targeting Locations

Find current geographic keys accepted by Meta ad targeting.

Send Media Message

Sends a media message (image, video, audio, or file) from the Page to a user.

Send Message

Sends a text message from a Facebook Page (not personal profiles) to a user via Messenger.

Set Page Profile Picture

Replace a managed Facebook Page's profile picture with an image fetched from a public HTTP or HTTPS URL.

Set Video Thumbnail

Upload a thumbnail image for a video owned by a managed Facebook Page and optionally make it preferred.

Toggle Typing Indicator

Shows or hides the typing indicator for a user in Messenger.

Unlike Post or Comment

Removes a like from a Facebook post or comment.

Update Comment

Updates an existing Facebook comment.

Update Page Settings

Updates settings for a specific Facebook Page.

Update Post

Updates an existing Facebook Page post.

Upload Photos Batch

Uploads independent photos to a Facebook Page or Album using the Graph batch API, accepting up to 50 local files and up to 50 photo URLs.

FAQ

Frequently asked questions

Start with Facebook.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Facebook tool your agent needs.Free to start.

Start building