MCPs
Facebook/Meta Ads MCP Server

Facebook/Meta Ads MCP Server

MCP server interface for secure, programmatic Meta Ads data and management.

View on GitHub

183

Stars

Forks

183

Watchers

Issues

Enables seamless integration between Model Context Protocol (MCP) clients and Meta (Facebook) Ads API, providing tools for programmatic data access and campaign management. Simplifies local installation with automated environment setup and optional secure authentication, eliminating the need for manual token retrieval. Designed for use with popular MCP clients such as Claude Desktop, offering plug-and-play connectivity. Data and tokens remain local for privacy and security.

Key Features

Local MCP server installation for Meta Ads integration

Programmatic access to Meta Ads data

Automated environment and dependency setup

Optional secure authentication via GoMarble's server

Supports MCP clients like Claude Desktop

Environment isolation with virtual environments

No manual token retrieval required

Sensitive tokens remain stored locally

Cross-platform Python support (3.10+)

Tools for Meta Ads campaign and data management

Use Cases

Automating Meta Ads campaign data retrieval

Securely managing Facebook advertising credentials

Integrating Meta Ads insights into business intelligence tools

Enhancing AI assistants with contextual Meta Ads data

Enabling marketing analytics workflows for agencies

Streamlining reporting for digital marketers

Building dashboards that visualize ad performance

Facilitating hands-free Meta Ads campaign management

Syncing ad data with CRM systems

Supporting A/B testing and campaign optimization workflows

README

Facebook/Meta Ads MCP Server

This project provides an MCP server acting as an interface to the Meta Ads, enabling programmatic access to Meta Ads data and management features.

Your browser does not support the video tag.

Easy One-Click Setup

For a simpler setup experience, we offer ready-to-use installers:

👉 Download installer - https://gomarble.ai/mcp

Join our community for help and updates

👉 Slack Community - AI in Ads

Try Google ads mcp server also

👉 Google Ads MCP - Google Ads MCP

What It Does

Installs and configures the MCP server locally
Automatically handles environment setup
Prompts for Meta token authentication during the process which is optional
If Meta access token is not provided then connect to GoMarble's server to create the token on your behalf

Important Disclaimer

This setup does not require you to manually obtain a Meta Developer Access Token.

Instead, it connects securely to GoMarble's server to create the token on your behalf. GoMarble does not store your token — it is saved locally on your machine for use with the MCP server.

Setup

Prerequisites

Python 3.10+
Dependencies listed in requirements.txt

(Optional but Recommended) Create and Activate a Virtual Environment:
bash
```
python3 -m venv venv
source venv/bin/activate  # On Windows use `venv\Scripts\activate`
```
Using a virtual environment helps manage project dependencies cleanly[Source].
Install Dependencies:
bash
```
pip install -r requirements.txt
```
Obtain Meta Access Token: Secure a Meta User Access Token with the necessary permissions (e.g., ads_read). You can generate this through the Meta Developer portal. Follow this link.

Usage with MCP Clients (e.g., Cursor, Claude Desktop)

To integrate this server with an MCP-compatible client, add a configuration(Claude) similar to the following. Replace YOUR_META_ACCESS_TOKEN with your actual token and adjust the path to server.py if necessary.

json

{
  "mcpServers": {
    "fb-ads-mcp-server": {
      "command": "python",
      "args": [
        "/path/to/your/fb-ads-mcp-server/server.py",
        "--fb-token",
        "YOUR_META_ACCESS_TOKEN"
      ]
      // If using a virtual environment, you might need to specify the python executable within the venv:
      // "command": "/path/to/your/fb-ads-mcp-server/venv/bin/python",
      // "args": [
      //   "/path/to/your/fb-ads-mcp-server/server.py",
      //   "--fb-token",
      //   "YOUR_META_ACCESS_TOKEN"
      // ]
    }
  }
}

Restart the MCP Client app after making the update in the configuration.

(Note: On Windows, you might need to adjust the command structure or use cmd /k depending on your setup.)

Debugging the Server

Execute server.py, providing the access token via the --fb-token argument.

bash

python server.py --fb-token YOUR_META_ACCESS_TOKEN

Available MCP Tools

This MCP server provides tools for interacting with META Ads objects and data:

Tool Name	Description
Account & Object Read
`list_ad_accounts`	Lists ad accounts linked to the token.
`get_details_of_ad_account`	Retrieves details for a specific ad account.
`get_campaign_by_id`	Retrieves details for a specific campaign.
`get_adset_by_id`	Retrieves details for a specific ad set.
`get_ad_by_id`	Retrieves details for a specific ad.
`get_ad_creative_by_id`	Retrieves details for a specific ad creative.
`get_adsets_by_ids`	Retrieves details for multiple ad sets by their IDs.
Fetching Collections
`get_campaigns_by_adaccount`	Retrieves campaigns within an ad account.
`get_adsets_by_adaccount`	Retrieves ad sets within an ad account.
`get_ads_by_adaccount`	Retrieves ads within an ad account.
`get_adsets_by_campaign`	Retrieves ad sets within a campaign.
`get_ads_by_campaign`	Retrieves ads within a campaign.
`get_ads_by_adset`	Retrieves ads within an ad set.
`get_ad_creatives_by_ad_id`	Retrieves creatives associated with an ad.
Insights & Performance Data
`get_adaccount_insights`	Retrieves performance insights for an ad account.
`get_campaign_insights`	Retrieves performance insights for a campaign.
`get_adset_insights`	Retrieves performance insights for an ad set.
`get_ad_insights`	Retrieves performance insights for an ad.
`fetch_pagination_url`	Fetches data from a pagination URL (e.g., from insights).
Activity/Change History
`get_activities_by_adaccount`	Retrieves change history for an ad account.
`get_activities_by_adset`	Retrieves change history for an ad set.

(Note: Most tools support additional parameters like fields, filtering, limit, pagination, date ranges, etc. Refer to the detailed docstrings within server.py for the full list and description of arguments for each tool.)

(Note: If your Meta access token expires, you'll need to generate a new one and update the configuration file of the MCP Client with new token to continue using the tools.)

Dependencies

mcp (>=1.6.0)
requests (>=2.32.3)

License

This project is licensed under the MIT License.

Installing via Smithery

To install Facebook Ads Server for Claude Desktop automatically via Smithery:

bash

npx -y @smithery/cli install @gomarble-ai/facebook-ads-mcp-server --client claude

Star History

Repository Owner

gomarble-ai

Organization

Repository Details

Language Python

Default Branch main

Size 123,014 KB

Contributors 5

License MIT License

MCP Verified Nov 12, 2025

Programming Languages

Python

99.55%

Dockerfile

0.45%

Related MCPs

Discover similar Model Context Protocol servers

Meta Ads MCP

AI-powered Meta Ads campaign analysis and management via MCP

Meta Ads MCP is a Model Context Protocol (MCP) server for managing, analyzing, and optimizing Meta advertising campaigns. It enables AI interfaces, such as LLMs, to retrieve ad performance data, visualize creatives, and provide strategic insights across Facebook, Instagram, and related platforms. The solution supports integration with platforms like Claude and Cursor, leveraging Meta's public APIs to deliver actionable insights and campaign management capabilities. Authentication options include interactive login and token-based flows for various MCP clients.

⭐ 342
MCP
pipeboard-co/meta-ads-mcp

Google Ads MCP Server

Seamlessly connect Google Ads API to MCP clients with automatic authentication and querying.

Google Ads MCP Server is a FastMCP-powered Model Context Protocol server designed to integrate Google Ads API with MCP clients such as Claude Desktop. It provides automatic OAuth 2.0 authentication, smart token management, GAQL query execution, and keyword research tools. The server enables users to manage accounts, run advanced queries, and generate keyword ideas while maintaining secure local token storage. Optimized for one-click setup, it offers robust features for advertisers and developers looking to leverage Google Ads data with MCP-compatible tools.

⭐ 76
MCP
gomarble-ai/google-ads-mcp-server

Tripadvisor MCP Server

Standardized MCP access to Tripadvisor travel data for AI assistants

Tripadvisor MCP Server provides Model Context Protocol (MCP) compliant access to Tripadvisor's Content API, enabling AI assistants to search, retrieve, and present travel-related information in a standardized way. It features endpoints for searching locations, accessing detailed information, reviews, and photos, as well as secure API key authentication. The project supports Docker containerization and interactive tools for customizable AI integration.

⭐ 47
MCP
pab1it0/tripadvisor-mcp

Dappier MCP Server

Real-time web search and premium data access for AI agents via Model Context Protocol.

Dappier MCP Server enables fast, real-time web search and access to premium data sources, including news, financial markets, sports, and weather, for AI agents using the Model Context Protocol (MCP). It integrates seamlessly with tools like Claude Desktop and Cursor, allowing users to enhance their AI workflows with up-to-date, trusted information. Simple installation and configuration are provided for multiple platforms, leveraging API keys for secure access. The solution supports deployment via Smithery and direct installation with 'uv', facilitating rapid setup for developers.

⭐ 35
MCP
DappierAI/dappier-mcp

amazon-ads-mcp-server

Stream Amazon Advertising data into MCP-compatible AI clients.

amazon-ads-mcp-server enables seamless integration of Amazon Advertising data—including campaigns, keywords, reports, and more—into any Model Context Protocol (MCP) compatible client. It provides both local and HTTP-based MCP server implementations for usage across desktops and platforms such as Claude Desktop and LibreChat. With support for plain English querying of reports and enhanced features like recommendations and experiments (with subscription), the tool facilitates streamlined access and interaction with Amazon Ads data for model-based workflows.

⭐ 18
MCP
MarketplaceAdPros/amazon-ads-mcp-server

Stape MCP Server

An MCP server implementation for integrating Stape with AI model context protocols.

Stape MCP Server provides an implementation of the Model Context Protocol server tailored for the Stape platform. It enables secure and standardized access to model context capabilities, allowing integration with tools such as Claude Desktop and Cursor AI. Users can easily configure and authenticate MCP connections using provided configuration samples, while managing context and credentials securely. The server is open source and maintained by the Stape Team under the Apache 2.0 license.

⭐ 4
MCP
stape-io/stape-mcp-server

View all Alternatives

Didn't find tool you were looking for?

Search AI Tools

Facebook/Meta Ads MCP Server

Key Features

Use Cases

README

Facebook/Meta Ads MCP Server

Easy One-Click Setup

Join our community for help and updates

Try Google ads mcp server also

What It Does

Important Disclaimer

Setup

Prerequisites

Usage with MCP Clients (e.g., Cursor, Claude Desktop)

Debugging the Server

Available MCP Tools

Dependencies

License

Installing via Smithery

Star History

Repository Owner

Repository Details

Programming Languages

Tags

Related MCPs