Borrowing it
Nothing to install: this file belongs to tools-mcp/vessel-traffic-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/tools-mcp/vessel-traffic-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/tools-mcp/vessel-traffic-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/tools-mcp/vessel-traffic-mcp/agents-md)<a href="https://agentmods.dev/instructions/tools-mcp/vessel-traffic-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/tools-mcp/vessel-traffic-mcp/agents-md.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 5.1 | $0.00652 | $0.00652 |
| Opus 5 | $0.00326 | $0.00326 |
| Sonnet 5 | $0.00130 | $0.00130 |
| Haiku 4.5 | $0.00065 | $0.00065 |
Grade A, and why
vessel-traffic-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.
How it starts
The opening of the file, as written. The whole thing — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Project Goal
Build vessel-traffic-mcp: a read-only Model Context Protocol server that lets ChatGPT, Claude, Claude Code, and other MCP clients query vessel identity, position, track, and port-call data from authorized AIS/maritime data sources.
Hard Rules
- Do not bypass authentication, paywalls, CAPTCHA, bot defenses, rate limits, or access controls.
- Do not implement credential harvesting, session hijacking, account sharing, or hidden scraping.
- Prefer official APIs and open-data feeds before any browser-network capture workflow.
- Browser/HAR capture support is for operator-owned, authorized sessions only, and only when the service terms allow that use.
- Paid/commercial providers are supported through BYOK credential profiles. Users may use their own provider subscriptions, but raw keys must be redacted and should not be pasted into normal chat unless a one-time in-memory mode is explicitly enabled.
- Never commit API keys, cookies, bearer tokens, CSRF tokens, session IDs, HAR files,
.env*, or raw private captures. - Sanitize all captured samples before storing fixtures. Strip
Authorization,Cookie,Set-Cookie, API keys, tokens, personal account IDs, and precise billing identifiers. - Keep MCP tools read-only. No tool may modify a provider account, fleet, billing setting, saved search, or user profile.
- Include source, timestamp, freshness, coverage caveats, and confidence in every vessel-position response.
- For B/L and shipping-document workflows, vessel-name resolution must return ranked MMSI/IMO candidates with evidence and must request confirmation when ambiguous.
- Treat missing AIS coverage, stale positions, and no-data responses as valid states, not implementation errors.
- Do not present AIS data as safety-critical navigation data.
Implementation Preferences
- Runtime: Node.js 22+, TypeScript, ESM.
- MCP SDK:
@modelcontextprotocol/sdk. - Primary transports: stdio for local Claude Desktop/Claude Code use, Streamable HTTP for remote ChatGPT/Claude connector use. SSE can be added only as compatibility fallback.
- Provider integrations must use adapter interfaces. Avoid provider-specific logic leaking into MCP tool handlers.
- For browser-only API capture, reference
<api-capture-checkout>architecture and docs, especially Playwright network capture, HAR backup, replay validation, traffic IR, supervisor pacing, and redaction. Do not read or copy its.env, raw sessions, raw logs, cookies, or credentials. The reference-only boundary is formalized indocs/runbooks/api-capture-reference-only.md(F5.AC5): raw api-capture sessions,.envfiles, cookies, and logs must never be imported into this project or committed. The operator-only execution workflow — triple-gated live driver, raw/sanitized artifact split, fixture promotion, and the rationale for excluding autodev/CI — is documented indocs/runbooks/capture-execution.md(F5A.AC3). - Tests should use sanitized fixtures and local fake providers. Do not call paid or live providers in default CI.
- Live-provider tests must be opt-in through environment variables and skipped by default.
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 · 31 lines · 652 tokens per session scan A 49c505363905
vessel-traffic-mcp AGENTS.md is an instructions file published in the GitHub repository tools-mcp/vessel-traffic-mcp (4 stars, last pushed 7d ago), licensed MIT. It adds 652 tokens to every session, about $0.0033 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
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.
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.
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).
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).
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.
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.