π βοΈ - Integrates with Facebook Pages to enable direct management of posts, comments, and engagement metrics through the Graph API for streamlined social media management.
What is Facebook?
Facebook is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to π βοΈ - integrates with facebook pages to enable direct management of posts, comments, and engagement metrics through the graph api for streamlined social media management.
π βοΈ - Integrates with Facebook Pages to enable direct management of posts, comments, and engagement metrics through the Graph API for streamlined social media management.
This server falls under the Communication category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- π βοΈ - Integrates with Facebook Pages to enable direct manag
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx facebookConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Facebook
The Facebook MCP Server connects AI assistants to your Facebook Pages via the Graph API, enabling direct management of posts, comments, and engagement metrics through natural language. It exposes 30+ tools covering content creation, comment moderation, analytics, and direct messaging. Developers and social media managers use it to automate workflows β scheduling posts, filtering negative comments, or pulling engagement reports β without leaving their AI chat interface.
Prerequisites
- Python 3.10+ and the uv package manager installed
- A Facebook Developer account with a registered app at developers.facebook.com
- A Facebook Page Access Token with manage_pages and publish_pages permissions
- Your Facebook Page ID (found in Page Settings)
- An MCP-compatible client such as Claude Desktop
Clone the repository
Download the server source code from GitHub to your local machine.
git clone https://github.com/HagaiHen/facebook-mcp-server.git
cd facebook-mcp-serverInstall dependencies with uv
Install the uv package manager if you don't have it, then install all Python dependencies.
curl -Ls https://astral.sh/uv/install.sh | bash
uv pip install -r requirements.txtCreate the .env file with credentials
Create a .env file in the project root with your Facebook Page Access Token and Page ID. Obtain these from the Graph API Explorer at developers.facebook.com/tools/explorer.
FACEBOOK_ACCESS_TOKEN=your_page_access_token_here
FACEBOOK_PAGE_ID=your_page_id_hereAdd the server to your MCP client configuration
Open your Claude Desktop config and add the FacebookMCP server entry, pointing to the server.py file you cloned.
Restart your MCP client and verify
Restart Claude Desktop. The Facebook MCP tools should now appear. Try asking 'What is my Facebook page fan count?' to verify the connection is working.
Facebook Examples
Client configuration
Add this to your claude_desktop_config.json, replacing the path with the actual location of server.py on your machine.
{
"mcpServers": {
"FacebookMCP": {
"command": "uv",
"args": [
"run",
"--with", "mcp[cli]",
"--with", "requests",
"mcp", "run",
"/absolute/path/to/facebook-mcp-server/server.py"
]
}
}
}Prompts to try
Once connected, use these prompts to manage your Facebook Page through your AI assistant.
- "Create a Facebook post announcing our new product launch scheduled for tomorrow at 10am"
- "Show me the engagement metrics for my last 5 Facebook posts"
- "Find all negative comments on my page from the last 7 days and hide them"
- "Reply to all unanswered comments on my latest post with a thank-you message"
- "What is the breakdown of reactions (likes, loves, wows) on my top post this week?"Troubleshooting Facebook
API returns 'Invalid OAuth access token' error
Facebook Page Access Tokens expire. Go to developers.facebook.com/tools/explorer, generate a new long-lived page access token, and update your FACEBOOK_ACCESS_TOKEN in the .env file.
Permission denied errors when posting or moderating comments
Your app or token is missing required permissions. In the Graph API Explorer, ensure your token includes manage_pages, publish_pages, and read_page_mailboxes permissions. You may also need to submit your app for Facebook App Review if it is not in development mode.
Server fails to start with 'module not found' errors
Run 'uv pip install -r requirements.txt' again from the project directory to ensure all dependencies are installed. If using a virtual environment, make sure it is activated before running the server.
Frequently Asked Questions about Facebook
What is Facebook?
Facebook is a Model Context Protocol (MCP) server that π βοΈ - integrates with facebook pages to enable direct management of posts, comments, and engagement metrics through the graph api for streamlined social media management. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Facebook?
Follow the installation instructions on the Facebook GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Facebook?
Facebook works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Facebook free to use?
Yes, Facebook is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
Facebook Alternatives β Similar Communication Servers
Looking for alternatives to Facebook? Here are other popular communication servers you can use with Claude, Cursor, and VS Code.
Slack
β 86.1kEnables interaction with Slack workspaces through comprehensive channel management, messaging, user management, file uploads, and Block Kit formatting. Features secure credential storage via macOS Keychain and supports all major Slack operations incl
LibreChat
β 37.3kEnhanced ChatGPT Clone: Features Agents, MCP, DeepSeek, Anthropic, AWS, OpenAI, Responses API, Azure, Groq, o1, GPT-5, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching, message search, Code Interpreter, langchain, DALL-E-3, OpenA
Note Gen
β 11.9kA cross-platform Markdown AI note-taking software.
DeepChat
β 5.8kπ¬DeepChat - A smart assistant that connects powerful AI to your personal world
WhatsApp MCP
β 5.7kConnects AI assistants to the official Meta WhatsApp Cloud API for managing conversations and sending various message types through natural language. It provides tools for media management, template messages, and real-time webhook processing without
Apple
β 3.1kEnables interaction with Apple apps like Messages, Notes, and Contacts through the MCP protocol to send messages, search, and open app content using natural language.
Browse More Communication MCP Servers
Explore all communication servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Facebook in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Facebook?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.