Borrowing it
Nothing to install: this file belongs to vantagemcp/vantage-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.
curl -O https://raw.githubusercontent.com/vantagemcp/vantage-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/vantagemcp/vantage-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/instructions/vantagemcp/vantage-mcp/agents-md)<a href="https://agentmods.dev/instructions/vantagemcp/vantage-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/vantagemcp/vantage-mcp/agents-md/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/instructions/vantagemcp/vantage-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/vantagemcp/vantage-mcp/agents-md.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 | $0.00463 | $0.00463 |
| Opus 5.5 | $0.00185 | $0.00185 |
| Sonnet 5.5 | $0.00093 | $0.00093 |
| Haiku 4.5 | $0.00046 | $0.00046 |
Grade A, and why
vantage-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 18d 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.
What it actually says
AGENTS.md
Notes for coding agents working in this repository.
What this is
Vantage is a Python MCP server that checks whether AI answer engines (ChatGPT, Gemini, Perplexity, Google AI
Overviews) cite a domain. It exposes ten read-only tools. The hosted copy runs at https://vantagemcp.dev/mcp;
this repo is the server only. Billing and account provisioning live in a separate internal service.
Layout
src/vantage_mcp/server.py: tool definitions (@mcp.tool), the stdio and--http(Streamable HTTP) transports.src/vantage_mcp/dataforseo_client.py: calls to the data provider and parsing of the answers it returns.src/vantage_mcp/auth.py,keys.py,store.py: OAuth sign-in, API keys, SQLite usage and saved checks.src/vantage_mcp/research.py: the monthly research run.mailer.py: the email that sends a copy of a key at sign-in.npm/: the stdio wrapper published asvantage-ai-visibility-mcp; it connects to the hosted server.
Run and check
uv venv && uv pip install -e .
export DATAFORSEO_USERNAME=... DATAFORSEO_PASSWORD=...
python -m vantage_mcp.server # stdio
python -m vantage_mcp.server --http # Streamable HTTP on VANTAGE_PORT (default 8420)
CI here only checks that vantage_mcp.server imports. The fuller test suite is kept with the maintainers' working
copy, so say in your pull request what you ran.
Rules that matter
- Every tool is read-only and returns structured data. Keep new tools read-only and annotated like the others.
- Metering happens before the paid provider call. A call that is rejected must never cost money.
- A tool's unit cost appears in its docstring and in the README tables. Change them together.
analyze_citation_gap'sfix_briefnever contains the cited answer's text. Keep it that way.- Never commit credentials. Provider credentials come from the environment.
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.
- 18d ago First seen · 38 lines · 463 tokens per session scan A da45068afa18
vantage-mcp AGENTS.md is an instructions file published in the GitHub repository vantagemcp/vantage-mcp (0 stars, last pushed 19d ago), licensed MIT. It adds 463 tokens to every session, about $0.0019 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 2026-10-21.
vantage-mcp AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| vantage-mcp AGENTS.mdvantagemcp/vantage-mcp | Instructions file | 0 | 19d ago | MIT | A | 463 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |