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 agentmods add instructions/willhou/admob-mcp/agents-mdgit clone --depth 1 https://github.com/willhou/admob-mcpWhat 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 | $0.01853 | $0.01853 |
| Opus 5 | $0.00927 | $0.00927 |
| Sonnet 5 | $0.00371 | $0.00371 |
| Haiku 4.5 | $0.00185 | $0.00185 |
Grade A, and why
admob-mcp AGENTS.md scanned grade A with 1 finding 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 2d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- `CONNECTOR_TOKEN` gates `/api/setup`, `/oauth/authorize`, and is also accepted as a direct bearer for `/api/mcp` (useful for curl-testing). Comparison is timing-safe. How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AdMob MCP Server
Local MCP server that connects Claude to the Google AdMob API via OAuth 2.0.
Build & Run
npm install
npm run build # tsc → dist/ (mirrors src/, api/, tests/)
npm test # vitest unit tests
npm run start # run stdio server on stdio
npm run dev:vercel # vercel dev (HTTP mode, requires .env.local)
npm run deploy # vercel deploy --prod
./setup.sh # interactive: pick local / vercel / both
./setup.sh --mode=local # non-interactive
./setup.sh --reauth # re-authorize (mode-aware)
Project Layout
src/index.ts— stdio MCP entry point. CallsregisterTools(server, getClient)withFileTokenStore.src/tools.ts— all tool definitions (6 core + 10 reporting + 20 optimization). ExportsregisterTools(server, getClient).src/auth.ts— OAuth helpers.getAuthenticatedClient(creds, store)is the headless refresh path used by both modes;authorizeViaLocalServer(creds, store)is the interactive CLI flow.src/authorize.ts— Standalone CLI script for OAuth authorization (run bysetup.shfor local mode).src/admob-client.ts— Thin REST client overhttps://admob.googleapis.com/v1.src/helpers.ts— Date math, report row parsing, table formatting, period-over-period change utils.src/token-store.ts—TokenStoreinterface,FileTokenStore(local),KvTokenStore(Vercel KV).src/oauth-store.ts— KV-backed storage for the connector OAuth flow: short-lived auth codes (oauth:authcode:<code>, 10-min TTL) and long-lived access tokens (oauth:token:<token>).src/http-auth.ts—checkBearer(sync, againstCONNECTOR_TOKEN) used by/oauth/authorizeand/api/setup;checkBearerAsync(also accepts KV-issued access tokens) used by/api/mcp.api/mcp.ts— Vercel function: Streamable HTTP MCP endpoint. Bearer-gated. ReturnsWWW-Authenticate: Bearer realm="admob-mcp", resource_metadata="…"on 401 per the MCP authorization spec.api/setup.ts— Vercel function: GET form + POST handler that initiates the Google ↔ server OAuth flow. Server's grant on AdMob.api/oauth/callback.ts— Vercel function: Google's redirect URI; stores tokens in KV.api/oauth/authorize.ts,api/oauth/token.ts,api/oauth/register.ts— Vercel functions implementing the Claude.ai ↔ server OAuth 2.1 flow with PKCE (S256) and Dynamic Client Registration. Required because Claude.ai's connector UI doesn't accept static bearer tokens — it negotiates its own access token.api/well-known/oauth-authorization-server.ts,api/well-known/oauth-protected-resource.ts— RFC 8414 / RFC 9728 metadata endpoints; reached at root paths (/.well-known/...) viavercel.jsonrewrites so Claude.ai's discovery works.vercel.json— Vercel function runtime + per-function timeouts + rewrites mapping/.well-known/*and/oauth/*to theapi/directory..env.example— Template for Vercel mode env vars.secrets/— Git-ignored. Local-modeclient_secret.jsonandtoken.jsonlive here.setup.sh— Interactive setup: pick[L]ocal/[V]ercel/[B]oth. Supports--mode=and--reauth.docs/VERCEL.md— Forker-facing deploy guide for the Connector path.tests/— vitest unit tests (token-store.test.ts,http-auth.test.ts).CLAUDE.md— Symlink to this file.
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.
- 2d ago First seen · 79 lines · 1,853 tokens per session scan A 1578246d6ada
admob-mcp AGENTS.md is an instructions file published in the GitHub repository willhou/admob-mcp (6 stars, last pushed 2mo ago), licensed MIT. It adds 1,853 tokens to every session, about $0.0093 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.