How to integrate Facebook MCP with Mastra AI

Framework Integration Gradient
Facebook Logo
Mastra AI Logo
divider

Introduction

This guide walks you through connecting Facebook to Mastra AI 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can post new product launch on our page, upload latest event photos to album, reply to comments on latest post, delete outdated promotional post through natural language commands.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 Mastra AI 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:
  • Set up your environment so Mastra, OpenAI, and Composio work together
  • Create a Tool Router session in Composio that exposes Facebook tools
  • Connect Mastra's MCP client to the Composio generated MCP URL
  • Fetch Facebook tool definitions and attach them as a toolset
  • Build a Mastra agent that can reason, call tools, and return structured results
  • Run an interactive CLI where you can chat with your Facebook agent

What is Mastra AI?

Mastra AI is a TypeScript framework for building AI agents with tool support. It provides a clean API for creating agents that can use external services through MCP.

Key features include:

  • MCP Client: Built-in support for Model Context Protocol servers
  • Toolsets: Organize tools into logical groups
  • Step Callbacks: Monitor and debug agent execution
  • OpenAI Integration: Works with OpenAI models via @ai-sdk/openai

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

Before starting, make sure you have:
  • Node.js 18 or higher
  • A Composio account with an active API key
  • An OpenAI API key
  • Basic familiarity with TypeScript

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key.
  • You need credits or a connected billing setup to use the models.
  • Store the key somewhere safe.
Composio API Key
  • Log in to the Composio dashboard.
  • Go to Settings and copy your API key.
  • This key lets your Mastra agent talk to Composio and reach Facebook through MCP.

Install dependencies

bash
npm install @composio/core @mastra/core @mastra/mcp @ai-sdk/openai dotenv

Install the required packages.

What's happening:

  • @composio/core is the Composio SDK for creating MCP sessions
  • @mastra/core provides the Agent class
  • @mastra/mcp is Mastra's MCP client
  • @ai-sdk/openai is the model wrapper for OpenAI
  • dotenv loads environment variables from .env

Set up environment variables

bash
COMPOSIO_API_KEY=your_composio_api_key_here
COMPOSIO_USER_ID=your_user_id_here
OPENAI_API_KEY=your_openai_api_key_here

Create a .env file in your project root.

What's happening:

  • COMPOSIO_API_KEY authenticates your requests to Composio
  • COMPOSIO_USER_ID tells Composio which user this session belongs to
  • OPENAI_API_KEY lets the Mastra agent call OpenAI models

Import libraries and validate environment

typescript
import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Agent } from "@mastra/core/agent";
import { MCPClient } from "@mastra/mcp";
import { Composio } from "@composio/core";
import * as readline from "readline";

import type { AiMessageType } from "@mastra/core/agent";

const openaiAPIKey = process.env.OPENAI_API_KEY;
const composioAPIKey = process.env.COMPOSIO_API_KEY;
const composioUserID = process.env.COMPOSIO_USER_ID;

if (!openaiAPIKey) throw new Error("OPENAI_API_KEY is not set");
if (!composioAPIKey) throw new Error("COMPOSIO_API_KEY is not set");
if (!composioUserID) throw new Error("COMPOSIO_USER_ID is not set");

const composio = new Composio({
  apiKey: composioAPIKey as string,
});
What's happening:
  • dotenv/config auto loads your .env so process.env.* is available
  • openai gives you a Mastra compatible model wrapper
  • Agent is the Mastra agent that will call tools and produce answers
  • MCPClient connects Mastra to your Composio MCP server
  • Composio is used to create a Tool Router session

Create a Tool Router session for Facebook

typescript
async function main() {
  const session = await composio.create(
    composioUserID as string,
    {
      toolkits: ["facebook"],
    },
  );

  const composioMCPUrl = session.mcp.url;
  console.log("Facebook MCP URL:", composioMCPUrl);
What's happening:
  • create spins up a short-lived MCP HTTP endpoint for this user
  • The toolkits array contains "facebook" for Facebook access
  • session.mcp.url is the MCP URL that Mastra's MCPClient will connect to

Configure Mastra MCP client and fetch tools

typescript
const mcpClient = new MCPClient({
    id: composioUserID as string,
    servers: {
      nasdaq: {
        url: new URL(composioMCPUrl),
        requestInit: {
          headers: session.mcp.headers,
        },
      },
    },
    timeout: 30_000,
  });

console.log("Fetching MCP tools from Composio...");
const composioTools = await mcpClient.getTools();
console.log("Number of tools:", Object.keys(composioTools).length);
What's happening:
  • MCPClient takes an id for this client and a list of MCP servers
  • The headers property includes the x-api-key for authentication
  • getTools fetches the tool definitions exposed by the Facebook toolkit

Create the Mastra agent

typescript
const agent = new Agent({
    name: "facebook-mastra-agent",
    instructions: "You are an AI agent with Facebook tools via Composio.",
    model: "openai/gpt-5",
  });
What's happening:
  • Agent is the core Mastra agent
  • name is just an identifier for logging and debugging
  • instructions guide the agent to use tools instead of only answering in natural language
  • model uses openai("gpt-5") to configure the underlying LLM

Set up interactive chat interface

typescript
let messages: AiMessageType[] = [];

console.log("Chat started! Type 'exit' or 'quit' to end.\n");

const rl = readline.createInterface({
  input: process.stdin,
  output: process.stdout,
  prompt: "> ",
});

rl.prompt();

rl.on("line", async (userInput: string) => {
  const trimmedInput = userInput.trim();

  if (["exit", "quit", "bye"].includes(trimmedInput.toLowerCase())) {
    console.log("\nGoodbye!");
    rl.close();
    process.exit(0);
  }

  if (!trimmedInput) {
    rl.prompt();
    return;
  }

  messages.push({
    id: crypto.randomUUID(),
    role: "user",
    content: trimmedInput,
  });

  console.log("\nAgent is thinking...\n");

  try {
    const response = await agent.generate(messages, {
      toolsets: {
        facebook: composioTools,
      },
      maxSteps: 8,
    });

    const { text } = response;

    if (text && text.trim().length > 0) {
      console.log(`Agent: ${text}\n`);
        messages.push({
          id: crypto.randomUUID(),
          role: "assistant",
          content: text,
        });
      }
    } catch (error) {
      console.error("\nError:", error);
    }

    rl.prompt();
  });

  rl.on("close", async () => {
    console.log("\nSession ended.");
    await mcpClient.disconnect();
    process.exit(0);
  });
}

main().catch((err) => {
  console.error("Fatal error:", err);
  process.exit(1);
});
What's happening:
  • messages keeps the full conversation history in Mastra's expected format
  • agent.generate runs the agent with conversation history and Facebook toolsets
  • maxSteps limits how many tool calls the agent can take in a single run
  • onStepFinish is a hook that prints intermediate steps for debugging

Complete Code

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

typescript
import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Agent } from "@mastra/core/agent";
import { MCPClient } from "@mastra/mcp";
import { Composio } from "@composio/core";
import * as readline from "readline";

import type { AiMessageType } from "@mastra/core/agent";

const openaiAPIKey = process.env.OPENAI_API_KEY;
const composioAPIKey = process.env.COMPOSIO_API_KEY;
const composioUserID = process.env.COMPOSIO_USER_ID;

if (!openaiAPIKey) throw new Error("OPENAI_API_KEY is not set");
if (!composioAPIKey) throw new Error("COMPOSIO_API_KEY is not set");
if (!composioUserID) throw new Error("COMPOSIO_USER_ID is not set");

const composio = new Composio({ apiKey: composioAPIKey as string });

async function main() {
  const session = await composio.create(composioUserID as string, {
    toolkits: ["facebook"],
  });

  const composioMCPUrl = session.mcp.url;

  const mcpClient = new MCPClient({
    id: composioUserID as string,
    servers: {
      facebook: {
        url: new URL(composioMCPUrl),
        requestInit: {
          headers: session.mcp.headers,
        },
      },
    },
    timeout: 30_000,
  });

  const composioTools = await mcpClient.getTools();

  const agent = new Agent({
    name: "facebook-mastra-agent",
    instructions: "You are an AI agent with Facebook tools via Composio.",
    model: "openai/gpt-5",
  });

  let messages: AiMessageType[] = [];

  const rl = readline.createInterface({
    input: process.stdin,
    output: process.stdout,
    prompt: "> ",
  });

  rl.prompt();

  rl.on("line", async (input: string) => {
    const trimmed = input.trim();
    if (["exit", "quit"].includes(trimmed.toLowerCase())) {
      rl.close();
      return;
    }

    messages.push({ id: crypto.randomUUID(), role: "user", content: trimmed });

    const { text } = await agent.generate(messages, {
      toolsets: { facebook: composioTools },
      maxSteps: 8,
    });

    if (text) {
      console.log(`Agent: ${text}\n`);
      messages.push({ id: crypto.randomUUID(), role: "assistant", content: text });
    }

    rl.prompt();
  });

  rl.on("close", async () => {
    await mcpClient.disconnect();
    process.exit(0);
  });
}

main();

Conclusion

You've built a Mastra AI agent that can interact with Facebook through Composio's Tool Router. You can extend this further by:
  • Adding other toolkits like Gmail, Slack, or GitHub
  • Building a web-based chat interface around this agent
  • Using multiple MCP endpoints to enable cross-app workflows

How to build Facebook MCP Agent with another framework

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 Mastra AI?

Yes, you can. Mastra AI 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.