How to integrate Facebook MCP with Autogen

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Facebook Logo
AutoGen Logo
divider

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can post new product launch on our page, upload latest event photos to album, reply to comments on latest post, delete outdated promotional post through natural language commands.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.

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.

Supported Tools & Triggers

Tools
Add Photos to AlbumAdds photos to an existing facebook album.
Add ReactionAdds a specific reaction (like, love, wow, etc.
Assign Page TaskAssigns tasks/roles to a user for a specific facebook page.
Create CommentCreates a comment on a facebook post or replies to an existing comment.
Create Photo AlbumCreates a new photo album on a facebook page.
Create Photo PostCreates a photo post on a facebook page.
Create PostCreates a new post on a facebook page.
Create Video PostCreates a video post on a facebook page.
Delete CommentDeletes a facebook comment.
Delete PostDeletes a facebook page post.
Get CommentRetrieves details of a specific facebook comment.
Get CommentsRetrieves comments from a facebook post or comment (for replies).
Get Conversation MessagesRetrieves messages from a specific conversation.
Get Message DetailsRetrieves details of a specific message sent or received by the page.
Get Page ConversationsRetrieves a list of conversations between users and the page.
Get Page DetailsFetches details about a specific facebook page.
Get Page InsightsRetrieves analytics and insights for a facebook page.
Get Page PhotosRetrieves photos from a facebook page.
Get Page PostsRetrieves posts from a facebook page.
Get Page RolesRetrieves a list of people and their tasks/roles on a facebook page.
Get Page VideosRetrieves videos from a facebook page.
Get PostRetrieves details of a specific facebook post.
Get Post InsightsRetrieves analytics and insights for a specific facebook post.
Get Post ReactionsRetrieves reactions (like, love, wow, etc.
Get Scheduled PostsRetrieves scheduled and unpublished posts for a facebook page.
Get User PagesRetrieves a list of pages the user manages, including tasks and access tokens.
Like Post or CommentLikes a facebook post or comment.
Mark Message SeenMarks a user's message as seen by the page.
Publish Scheduled PostPublishes a previously scheduled or unpublished facebook post immediately.
Remove Page TaskRemoves a user's tasks/access from a specific facebook page.
Reschedule PostChanges the scheduled publish time of an unpublished facebook post.
Send Media MessageSends a media message (image, video, audio, or file) from the page to a user.
Send MessageSends a text message from the page to a user via messenger.
Toggle Typing IndicatorShows or hides the typing indicator for a user in messenger.
Unlike Post or CommentRemoves a like from a facebook post or comment.
Update CommentUpdates an existing facebook comment.
Update Page SettingsUpdates settings for a specific facebook page.
Update PostUpdates an existing facebook page post.
Upload PhotoUploads a photo file directly to a facebook page.
Upload Photos BatchUploads multiple photo files in batch to a facebook page or album.
Upload VideoUploads a video file directly to a facebook page.

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

What is Tool Router?

Composio's Tool Router 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 Tool Router

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

How the Tool Router works

The Tool Router 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

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

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.

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

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

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

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

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

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.

How to build Facebook MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Facebook MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Facebook MCP with Claude Agent SDK

Google ADK

Google ADK

Use Facebook MCP with Google ADK

LangChain

LangChain

Use Facebook MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Facebook MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Facebook MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Facebook MCP with LlamaIndex

CrewAI

CrewAI

Use Facebook MCP with CrewAI

FAQ

What are the differences in Tool Router MCP and Facebook MCP?

With a standalone Facebook MCP server, the agents and LLMs can only access a fixed set of Facebook tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Facebook and many other apps based on the task at hand, all through a single MCP endpoint.

Can I use Tool Router MCP with Autogen?

Yes, you can. Autogen fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Facebook tools.

Can I manage the permissions and scopes for Facebook while using Tool Router?

Yes, absolutely. You can configure which Facebook scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

How safe is my data with Composio Tool Router?

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Facebook data and credentials are handled as safely as possible.

Used by agents from

Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.

Book a call↗Get started for free