How does it differ from other Meta Ads MCP tools?
This server focuses on historical analysis and marketing intelligence (e.g., fatigue, decay, leaks), not live campaign management. It works offline and includes sample data for testing.
@shibanshu12
Basic information
Performance marketing diagnostics MCP server for Meta Ads. 15 tools for spend leak detection, creative fatigue analysis, audience decay monitoring, benchmarking, and custom SQL queries. Read-only SQLite security by default.
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"meta-ads-analyzer": {
"command": "uv",
"args": [
"run",
"--with",
"meta-ads-analyzer",
"meta-ads-analyzer"
],
"env": {
"META_ADS_DB_PATH": "/path/to/your/meta_ads_data.db"
}
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
An MCP server that turns your Meta Ads data into a conversational analytics layer. It stores historical campaign data locally and lets you query it with natural language via Claude. Built for advertisers and media buyers who need deeper campaign intelligence than Ads Manager charts provide.
Install pip install meta-ads-analyzer, then add the server to your Claude Desktop config with the META_ADS_DB_PATH environment variable pointing to a SQLite database. Optionally pull your own Meta Ads data using the provided pipeline and your API credentials, or test immediately with included sample data.
This server focuses on historical analysis and marketing intelligence (e.g., fatigue, decay, leaks), not live campaign management. It works offline and includes sample data for testing.
Requires Python 3.10+, a Claude Pro or Max subscription (MCP servers only work with Claude Desktop, Claude Code, or Claude.ai), and optionally

Verified distributed compute for humans, applications, and agents. Submit Blender, Octane, and video workloads, route them across qualified GPUs, track asynchronous execution, download finished artifacts, and verify FARP

MCP server for AI Agents — exposes Yocoolab feedback threads and design selections as tools

AI SEO tools for MCP clients — audit whether AI crawlers can read a website, validate JSON-LD and robots.txt, and generate llms.txt, AI-crawler-aware robots.txt, and JSON-LD schema without leaving the conversation.
Gives AI agents public URLs (tunnels) for localhost, live HTTP traffic inspection, snapshot publishing, and access control. Part of LocalCan, the ngrok alternative for Mac, Windows and Linux. Free plan.

The tools your AI needs to make your games. Turn prompts into production-ready game assets — animated characters with their weapons attached, seamless textures, terrain, VFX, HUDs — and playable game kits Unity, Godot, U
Comments