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.
npx skills add byadsco/meta-ads-mcp --skill meta-ads-mcp-guidegit clone --depth 1 https://github.com/byadsco/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/skills/byadsco/meta-ads-mcp/meta-ads-mcp-guide)<a href="https://agentmods.dev/skills/byadsco/meta-ads-mcp/meta-ads-mcp-guide"><img src="https://agentmods.dev/badge/skills/byadsco/meta-ads-mcp/meta-ads-mcp-guide/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/skills/byadsco/meta-ads-mcp/meta-ads-mcp-guide"><img src="https://agentmods.dev/badge/skills/byadsco/meta-ads-mcp/meta-ads-mcp-guide.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00104 | $0.01205 |
| Opus 5.5 | $0.00042 | $0.00482 |
| Sonnet 5.5 | $0.00021 | $0.00241 |
| Haiku 4.5 | $0.00010 | $0.00120 |
Grade A, and why
meta-ads-mcp-guide 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working with meta-ads-mcp
This server brokers the Meta Marketing API for advertising agencies. It is multi-tenant: every call runs as one authenticated advertiser, and the credentials belong to them, not to the server.
Three things are worth knowing before the first call.
Reads are free, writes are not. A ⚠️ in a tool description means it changes live ads, spends the advertiser's money, or touches their stored credentials. Never call one to "see what happens".
The server already batches. Several tools exist precisely so an agent does not have to make ten calls and stitch the answers together. Reach for those first; the tool map says which.
Meta's errors are usually about inputs. An ID of the wrong kind, an objective that cannot change, a breakdown Meta refuses at that level. The server rejects the known-bad combinations before spending a call, and its error messages say what to do instead. Read them.
Choosing a tool
references/tool-map.md lists all 142 grouped by intent. The shortest path for the common asks:
| The ask | Start with |
|---|---|
| "How is this ad doing?" | ads_get_ad_dossier — ad, ad set, campaign, creative, targeting, performance and media in one call |
| "Why is this underperforming?" | ads_diagnose_underperformance, then the dossier for the ad it points at |
| "Show me the creative" | ads_get_creative_media; for video, see the video-analysis skill |
| "What is the competition running?" | the competitor-research skill; it costs money, so read it first |
| "Give me numbers" | ads_get_insights, or a named view like ads_insights_performance_trend |
| "Change something" | the specific write tool, after confirming with the human |
When no account id is known, ads_get_ad_accounts is the entry point. When a money figure matters, ads_get_account_info first: budgets come back in the account currency's minor units, and a figure without its currency is meaningless.
Before you write
Writes are irreversible in practice. Meta has no undo, and a deleted campaign takes its history with it.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 65 lines · 104 tokens per session scan A d80b9e0fed42
meta-ads-mcp-guide is a skill published in the GitHub repository byadsco/meta-ads-mcp (24 stars, last pushed today), licensed MIT. It adds 104 tokens to every session and 1,205 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-18.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…