Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/mikusnuz/meta-ads-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/mcp/mikusnuz/meta-ads-mcp/meta-ads)<a href="https://agentmods.dev/mcp/mikusnuz/meta-ads-mcp/meta-ads"><img src="https://agentmods.dev/badge/mcp/mikusnuz/meta-ads-mcp/meta-ads/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/mcp/mikusnuz/meta-ads-mcp/meta-ads"><img src="https://agentmods.dev/badge/mcp/mikusnuz/meta-ads-mcp/meta-ads.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
meta-ads scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"meta-ads": {
"command": "npx",
"args": [
"-y",
"@mikusnuz/meta-ads-mcp"
],
"env": {
"META_ADS_ACCESS_TOKEN": "",
"META_AD_ACCOUNT_ID": "",
"META_APP_ID": "",
"META_APP_SECRET": "",
"META_BUSINESS_ID": "",
"META_PIXEL_ID": ""
}
}
}What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 17 lines scan A fa84c3a8d884
meta-ads is an MCP server published in the GitHub repository mikusnuz/meta-ads-mcp (76 stars, last pushed 15d ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other mcp servers, from other repositories
dynamoi
Create music promotion campaigns, Smart Links, analytics, and music distribution applications. Runs locally from the @dynamoi/mcp npm package.
meta-ads
Meta (Facebook and Instagram) Ads: 34 read tools and 10 write tools that preview first. Runs locally from the @getmcpads/meta-ads-mcp-server npm package. Needs 3 environment variables to run.
meta-ads-mcp
Model Context Protocol (MCP) server for Meta Ads - Use Remote MCP at pipeboard.co for easiest setup. Runs locally from the meta-ads-mcp Python package.
google-meta-ads-ga4-mcp
Google Ads, Meta Ads & GA4 MCP server - 250+ tools for campaigns, creatives, audiences & reports. Remote server at mcp.get-ryze.ai.
google-meta-ads-ga4
MCP server "google-meta-ads-ga4", hosted remotely at connector.get-ryze.ai, as configured in irinabuht12-oss/google-meta-ads-ga4-mcp.
zuckerbot
CLI + MCP server for ZuckerBot — manage, audit and generate Meta ad campaigns from Claude or any AI agent. Runs locally from the zuckerbot-mcp npm package. Needs 1 environment variable to run.