What is meta-ads-mcp AGENTS.md?

Repository instructions for meta-ads-mcp, a server that lets agencies access the Meta advertising API through the Model Context Protocol. They describe its technology stack, naming rules, and checks before deployment or commits.

Use them when adding or changing advertising tools, authentication, token storage, tests, or deployment code in this repository.

They make the project’s API, security, and deployment conventions explicit for coding agents. This helps prevent incompatible tool names, outdated registration methods, and unsafe changes before release.

How byadsco/meta-ads-mcp configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to byadsco/meta-ads-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/byadsco/meta-ads-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/byadsco/meta-ads-mcp

Made for: Claude Code, Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/byadsco/meta-ads-mcp/agents-md.svg)](https://agentmods.dev/instructions/byadsco/meta-ads-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/byadsco/meta-ads-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/byadsco/meta-ads-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 2,098 This file is loaded in full into every session.

When invoked 2,098 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.02098	$0.02098
Opus 5	$0.01049	$0.01049
Sonnet 5	$0.00420	$0.00420
Haiku 4.5	$0.00210	$0.00210

Measured 8d ago against content hash b61f6f30df31, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

meta-ads-mcp AGENTS.md 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 8d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

meta-ads-mcp AGENTS.md — 100% identical, 0 lines differ

AGENTS.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

meta-ads-mcp — agent guide

Project memory for Codex (and any other AI assistant). This file is committed and shared with everyone working on the repo.

What this project is

A Model Context Protocol server that brokers Meta Ads API access for advertising agencies. Multi-tenant, OAuth-gated, with encrypted-at-rest token storage in Firestore. Deployed to Google Cloud Run.

Stack: Node 20.10+, TypeScript (ESM), Express 5, vitest, Pino, Zod, Firestore. MCP SDK 1.29 (registerTool API + ToolAnnotations).
Entry: src/index.ts → src/transport/http.ts.
Deploy: push to main triggers .github/workflows/deploy.yml. PRs trigger .github/workflows/ci.yml.
License: MIT. Repository is public on GitHub.

Conventions specific to this repo (v3.0.0+)

Tool naming: ads_* prefix (no meta_). ad_set with underscore (not adset). Aligned with Meta's official MCP server (mcp.facebook.com/ads). See docs/migration-v3.md for the full rationale.
Tool registration: always server.registerTool(name, { description, inputSchema, annotations }, handler). The legacy server.tool(...) API is removed.
Annotations: every tool spreads one of the constants from src/tools/_register.ts (READ / CREATE / UPDATE / DELETE / TOGGLE / UPLOAD / TOKEN) into its annotations field. Write tools prepend WRITE_WARNING to the description.
Adding tools: see docs/adding-a-tool.md for the full template + checklist.

⚠️ Pre-deploy / pre-commit safety rule

This repo is public. Anything pushed to GitHub is permanent and indexed by search engines and bots within seconds. Treat every commit as a one-way door.

Before any git commit -m, git push, gcloud run deploy, docker push, npm publish, or PR merge, the following must be true:

npm run lint passes.
npm run typecheck passes.
npm test passes (runs vitest).
npm run build passes (TypeScript build).
No prohibited files in staging: .env, .env.* (except .env.example), *.key, *.pem, credentials.json, service-account*.json, SSH private keys, *.p12, *.pfx.
gitleaks detect --staged --config .gitleaks.toml finds no secrets.
No project-specific patterns appear in the staged diff. Custom regex covers (full list in .gitleaks.toml):
- META_APP_SECRET=, OAUTH_SECRET=, OAUTH_APPROVAL_PIN=, SESSION_COOKIE_SECRET=, TOKEN_ENCRYPTION_KEY=, MCP_API_KEY=
- Meta access tokens: EAA[A-Za-z0-9]{20,}
- META_TOKENS={…EAA…} (multi-tenant token map)
- Google: AIza[A-Za-z0-9_-]{35}, ya29\.[A-Za-z0-9_-]+, GCP service account JSON
- Generic: -----BEGIN … PRIVATE KEY-----, GitHub PATs (gh[pousr]_), AWS keys (AKIA)
.gitignore covers .env, .env.local, *.key, *.pem, credentials.json, service-account*.json, dist/, node_modules/.

Read the full file on GitHub · 126 lines

Changes

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.

8d ago First seen · 126 lines · 2,098 tokens per session scan A b61f6f30df31

Subscribe to this mod's changes

meta-ads-mcp AGENTS.md is an instructions file published in the GitHub repository byadsco/meta-ads-mcp (14 stars, last pushed 4d ago), licensed MIT. It adds 2,098 tokens to every session, about $0.0105 per session on Opus 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 2026-08-30.

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

meta-ads-mcp: Instructions file for Claude Code