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/appsyogi-com/adsense-mcp-server/copilot-instructionsgit clone --depth 1 https://github.com/AppsYogi-com/adsense-mcp-serverWrote 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/instructions/appsyogi-com/adsense-mcp-server/copilot-instructions)<a href="https://agentmods.dev/instructions/appsyogi-com/adsense-mcp-server/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/appsyogi-com/adsense-mcp-server/copilot-instructions.svg" alt="Measured on agentmods" 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 | $0.00686 | $0.00686 |
| Opus 5 | $0.00343 | $0.00343 |
| Sonnet 5 | $0.00137 | $0.00137 |
| Haiku 4.5 | $0.00069 | $0.00069 |
Grade A, and why
adsense-mcp-server copilot-instructions.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 5d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AdSense-MCP Copilot Instructions
Project Overview
This is a Model Context Protocol (MCP) server that provides Google AdSense API access to AI clients (Claude, Cursor, VS Code Copilot). It's distributed as a CLI tool via npm (adsense-mcp) with OAuth/service account authentication.
Architecture
src/
├── index.ts # Public exports for programmatic use
├── types.ts # TypeScript types (single source of truth)
├── cli/ # Commander-based CLI (`adsense-mcp init|doctor|run`)
├── server/ # MCP server implementation
│ ├── index.ts # Server factory with stdio transport
│ ├── tools/ # MCP tools organized by domain
│ └── resources/ # MCP resources
├── adsense/
│ ├── client.ts # AdSense API wrapper with all operations
│ ├── rateLimiter.ts # Rate limiting with exponential backoff
│ └── cache.ts # SQLite cache with TTL
└── auth/ # OAuth2 + service account auth, token storage
Key data flows:
- CLI commands →
createServer()→ MCP stdio transport - Tool calls →
handleToolCall()routes to domain handlers →AdSenseClient→ Google API - Tokens stored via
keytar(OS keychain) with file fallback; config inenv-pathsdirectories
Development Commands
npm run build # tsup build (ESM, Node 18+)
npm run dev # Watch mode
npm run typecheck # tsc --noEmit
npm run lint # eslint src/
adsense-mcp doctor # Check auth and API access
Code Conventions
Adding New MCP Tools
- Create tool definition in
src/server/tools/<domain>.tsfollowing the pattern:- Export handler function like
handle<Action>(args)
- Export handler function like
- Register in
src/server/tools/index.ts:- Add tool schema to
registerTools()array - Add case to
handleToolCall()switch
- Add tool schema to
- Tool names use underscore notation:
adsense_earnings_summary,adsense_list_sites
Type Definitions
- Define types in
src/types.ts - Tool input schemas use plain JSON Schema format for MCP
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.
- 5d ago First seen · 78 lines · 686 tokens per session scan A 551778701623
adsense-mcp-server copilot-instructions.md is an instructions file published in the GitHub repository AppsYogi-com/adsense-mcp-server (5 stars, last pushed 7mo ago), licensed MIT. It adds 686 tokens to every session, about $0.0034 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 2026-08-31.
Other instructions, from other repositories
notebooklm-mcp-2026 CLAUDE.md
Instructions for julianoczkowski/notebooklm-mcp-2026, covering claude.md, what this project is, commands, install and lint.
notebooklm-mcp GEMINI.md
Instructions for m4yk3ldev/notebooklm-mcp, covering notebooklm mcp server - project context, project overview, key technologies, architecture and building and running.
notebooklm-mcp CLAUDE.md
Instructions for m4yk3ldev/notebooklm-mcp, covering claude.md, commands, install dependencies (pnpm pinned via packagemanager field), build (outputs to dist/) and watch mode for development.
mcp-youtube CLAUDE.md
Claude Code instructions for kud/mcp-youtube, covering mcp-youtube and api reference.
blockrun-mcp AGENTS.md
AGENTS.md instructions for BlockRunAI/blockrun-mcp, covering blockrun mcp, commands, project structure, key dependencies and install in codex.
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).