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/RoyAzran/mcp-adsWrote 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/plugins/royazran/mcp-ads/plugin)<a href="https://agentmods.dev/plugins/royazran/mcp-ads/plugin"><img src="https://agentmods.dev/badge/plugins/royazran/mcp-ads/plugin/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/plugins/royazran/mcp-ads/plugin"><img src="https://agentmods.dev/badge/plugins/royazran/mcp-ads/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
mcp-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 today.
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
{
"name": "mcp-ads",
"version": "1.1.0",
"description": "Google Ads, Meta, LinkedIn, TikTok, Snapchat, Microsoft Advertising, GA4 and Search Console as tools for Claude, plus an ads-manager skill. Every write waits for your approval.",
"author": {
"name": "Roy Azran",
"url": "https://mcp-ads.com"
},
"homepage": "https://mcp-ads.com",
"repository": "https://github.com/RoyAzran/mcp-ads",
"license": "MIT",
"keywords": [
"ads",
"google-ads",
"meta-ads",
"marketing",
"ppc",
"ga4",
"search-console"
]
}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.
- today First seen · 21 lines scan A e38cd3d1cc74
mcp-ads is a plugin published in the GitHub repository RoyAzran/mcp-ads (2 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-10-17.
Other plugins, from other repositories
onplana
Plan and run projects in Onplana from Claude Code. Describe the work and get a real plan back: epics, tasks, estimates, dependencies and scheduled dates. Ships the Onplana project-planning and autonomous-agent skills, and connects to the Onplana MCP server, with /onplana-connect to sign in.
onplana
Connect Gemini CLI + Gemini Code Assist to Onplana. Read and update projects, tasks, sprints, comments, risks, milestones, and team members. Search across your org's indexed content (vector + BM25 RAG). Audited, plan-gated, prompt-injection-contained.
whooshly
Create short links, dynamic QR codes, UTM templates, hosted vCards, and landing pages with lead capture from Claude. Connects to Whooshly's hosted remote MCP server.
secedgar-mcp-server
Query SEC EDGAR filings, XBRL financials, and company data via MCP. STDIO or Streamable HTTP.
cdc-health-mcp-server
Search and query CDC public health data — mortality, vaccinations, surveillance, behavioral risk (Socrata SODA API) via MCP. STDIO or Streamable HTTP.
promptspeak
Pre-execution governance for AI agents. Intercepts MCP tool calls with deterministic blocking, human-in-the-loop holds, and behavioral drift detection.