facebook-ads-mcp-server  by gomarble-ai

Meta Ads MCP server for programmatic access and management

Created 1 year ago
265 stars

Top 96.3% on SourcePulse

GitHubView on GitHub
Project Summary

Summary

This project provides a local MCP server interface for Meta Ads, enabling programmatic access to ad data and management features. It targets developers and power users seeking to automate Meta Ads interactions, offering simplified setup and optional token generation via GoMarble's secure service.

How It Works

The MCP server installs and configures itself locally, automating environment setup and prompting for Meta token authentication. If a user-provided token is absent, it securely connects to GoMarble's server to generate one, which is then saved locally without being stored by GoMarble. This acts as a bridge for MCP-compatible clients.

Quick Start & Requirements

  • Prerequisites: Python 3.10+.
  • Dependencies: mcp (>=1.6.0), requests (>=2.32.3), and others listed in requirements.txt.
  • Installation:
    1. Create/activate a virtual environment (python3 -m venv venv && source venv/bin/activate).
    2. Install dependencies (pip install -r requirements.txt).
    3. Obtain a Meta User Access Token with ads_read permissions or allow the server to generate one.
  • Usage: Configure MCP clients (e.g., Claude Desktop) with the server's server.py path and token.
  • Automatic Install: npx -y @smithery/cli install @gomarble-ai/facebook-ads-mcp-server --client claude for Claude Desktop.
  • Docs/Demos: Installer available at https://gomarble.ai/mcp.

Highlighted Details

  • Comprehensive Tooling: Offers granular access to Meta Ads objects (accounts, campaigns, ad sets, ads, creatives) and performance insights.
  • Data Fetching: Supports fetching collections, insights, and activity/change history with extensive parameterization (fields, filtering, pagination, date ranges).
  • Simplified Token Management: Optional secure token generation via GoMarble's service, avoiding manual Meta Developer portal steps for users.
  • MCP Integration: Designed to work seamlessly with MCP-compatible clients for conversational AI-driven ad management.

Maintenance & Community

  • Community: A Slack community is available for help and updates (AI in Ads).

Licensing & Compatibility

  • License: MIT License.
  • Compatibility: Permissive MIT license allows for commercial use and integration into closed-source applications.

Limitations & Caveats

Meta access tokens are subject to expiration, requiring re-authentication or token regeneration. The optional token generation relies on an external service, which may be a consideration for users with strict data handling policies. Integration requires specific configuration within compatible MCP client applications.

Health Check
Last Commit

7 months ago

Responsiveness

Inactive

Pull Requests (30d)
0
Issues (30d)
0
Star History
16 stars in the last 30 days

Explore Similar Projects

Starred by Chip Huyen Chip Huyen(Author of "AI Engineering", "Designing Machine Learning Systems"), Kent Dodds Kent Dodds(Cofounder of Remix), and
10 more.

agentic by transitive-bullshit

0.0%
18k
AI agent stdlib for LLM-based TypeScript tooling
Created 3 years ago
Updated 2 months ago
Feedback? Help us improve.