plausible-mcp AGENTS.md

A set of repository instructions for Plausible MCP, a server that connects AI agents to Plausible’s website statistics API. It explains which checks to run, where security and privacy guidance lives, and how the project is structured.

In plain words
What is it for?
Building and testing Plausible MCP changes, checking its Node and Cloudflare Worker code, and handling telemetry, configuration, authentication, and releases correctly.
Why use it?
It prevents incomplete validation when changes affect both the standard server and the Cloudflare Worker, and points contributors to the project’s privacy and deployment rules.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/getsentry/plausible-mcp/agents-md
Clone the repo
git clone --depth 1 https://github.com/getsentry/plausible-mcp

Made for: Codex, OpenCode.

Per session 265 This file is loaded in full into every session.
When invoked 265 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00265 $0.00265
Opus 5 $0.00133 $0.00133
Sonnet 5 $0.00053 $0.00053
Haiku 4.5 $0.00026 $0.00026

Measured 2d ago against content hash 5059eb41ef2f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plausible-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 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.

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.

AGENTS.md · 14 lines

What it actually says

MCP server wrapping the Plausible Stats API v2. Two entry points — STDIO (src/index.ts) and a Cloudflare Worker (src/worker.ts) — so a change to shared code usually needs both checked.

Before calling a change green

pnpm build does not typecheck the Worker. worker.ts, env.ts and cf-access.ts use Workers globals rather than Node ones, so tsconfig.json excludes them and pnpm typecheck covers them through tsconfig.worker.json. Run both, plus pnpm test.

craft owns the version in package.json and every CHANGELOG.md line — leave both to the release pipeline.

Reference

  • Sentry, spans, metrics, or anything user-identifyingTELEMETRY.md, which owns the privacy posture: /mcp anonymous, /internal attributed.
  • Deploying, or the Worker's auth and endpoints — README "Self-Hosting". SENTRY_DSN stays an uncommitted secret; a hardcoded one once had forks of this public repo reporting into our Sentry project.
  • Scripts are in package.json, environment variables in README "Configuration", contributor procedure in CONTRIBUTING.md.
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.

  1. 2d ago First seen · 14 lines · 265 tokens per session scan A 5059eb41ef2f

Subscribe to this mod's changes

plausible-mcp AGENTS.md is an instructions file published in the GitHub repository getsentry/plausible-mcp (38 stars, last pushed 5d ago), licensed MIT. It adds 265 tokens to every session, about $0.0013 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.