meta-ads-mcp  by pipeboard-co

AI for Meta Ads campaign management

Created 11 months ago
678 stars

Top 49.8% on SourcePulse

GitHubView on GitHub
Project Summary

This project provides a Model Context Protocol (MCP) server for managing Meta (Facebook/Instagram) Ads, enabling AI models to interact with the Meta Ads API. It's designed for marketers and developers who want to leverage AI for ad campaign analysis, optimization, and management, offering both a convenient remote cloud service and a local installation option.

How It Works

The Meta Ads MCP acts as a bridge between AI models and the Meta Ads API. It exposes a set of tools (functions) that LLMs can call to perform various ad management tasks, such as retrieving campaign data, creating ads, and analyzing performance. The project supports streamable HTTP transport, allowing for scalable and reliable data access, and emphasizes a standardized interface for broad compatibility with different AI clients.

Quick Start & Requirements

  • Remote MCP (Recommended): Connect via claude.ai/settings/integrations or other MCP clients using the URL https://mcp.pipeboard.co/meta-ads-mcp. No technical setup required.
  • Local Installation: Recommended for technical users. Install via uvx meta-ads-mcp and set PIPEBOARD_API_TOKEN. Requires a Pipeboard token. Detailed instructions are in LOCAL_INSTALLATION.md.

Highlighted Details

  • AI-Powered Campaign Analysis and Strategic Recommendations.
  • Automated Monitoring, Budget Optimization, and Creative Improvement suggestions.
  • Supports Dynamic Creative Testing and Campaign Management with explicit confirmation.
  • Universal LLM Support, compatible with clients like Claude Desktop, Cursor, and Cherry Studio.

Maintenance & Community

  • Community support is available via Discord and email.
  • The project is maintained independently and is not affiliated with Meta.

Licensing & Compatibility

  • Licensed under the Business Source License 1.1. Free for individual and business use, with modification and redistribution allowed. Becomes fully Apache 2.0 open-source on January 1, 2029.
  • Restriction: Cannot be offered as a competing hosted service. Commercial licensing inquiries are directed to the maintainers.

Limitations & Caveats

  • The project is an unofficial third-party tool and is not endorsed by Meta.
  • Local installation is for technical users; marketers are encouraged to use the Remote MCP to avoid setup complexities.
Health Check
Last Commit

1 day ago

Responsiveness

Inactive

Pull Requests (30d)
14
Issues (30d)
4
Star History
172 stars in the last 30 days

Explore Similar Projects

Starred by Chip Huyen Chip Huyen(Author of "AI Engineering", "Designing Machine Learning Systems"), Pietro Schirano Pietro Schirano(Founder of MagicPath), and
1 more.

SillyTavern by SillyTavern

1.1%
25k
LLM frontend for power users
Created 3 years ago
Updated 1 day ago
Starred by Chip Huyen Chip Huyen(Author of "AI Engineering", "Designing Machine Learning Systems"), Jasper Zhang Jasper Zhang(Cofounder of Hyperbolic), and
7 more.

anything-llm by Mintplex-Labs

0.5%
57k
All-in-one AI app with built-in RAG, agents, and no-code agent builder
Created 2 years ago
Updated 1 day ago
Feedback? Help us improve.