What is mcp AGENTS.md?

Project instructions for a Piwik PRO MCP server, a connector that exposes Piwik PRO analytics functions to an AI assistant. They cover setup, code structure, configuration, tests, and communication methods.

Use them when setting up the project, adding or modifying analytics tools, updating configuration, and running its tests, linting, and formatting checks.

They give contributors the commands and architectural rules needed to change the server safely and verify that it still works.

How PiwikPRO/mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to PiwikPRO/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.

Copy the file

curl -O https://raw.githubusercontent.com/PiwikPRO/mcp/master/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/PiwikPRO/mcp

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/piwikpro/mcp/agents-md/github.svg)](https://agentmods.dev/instructions/piwikpro/mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/piwikpro/mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/piwikpro/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/piwikpro/mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/piwikpro/mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 850 This file is loaded in full into every session.

When invoked 850 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00850	$0.00850
Opus 5.5	$0.00340	$0.00340
Sonnet 5.5	$0.00170	$0.00170
Haiku 4.5	$0.00085	$0.00085

Measured 1mo ago against content hash e111e3a1715e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 1mo 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 · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Setup & Verify

Use uv for everything. Install deps with uv sync --dev.
Python requirement is >=3.12.
Run the server with uv run python -m piwik_pro_mcp.server or uv run piwik-pro-mcp.
Match CI before finishing: uv run pytest -v --tb=short, uv run ruff check . --config pyproject.toml, then uv run ruff format --check . --config pyproject.toml.
For focused checks, tests live under src/piwik_pro_mcp/tests, so use commands like uv run pytest src/piwik_pro_mcp/tests/test_server.py::TestMain::test_main_defaults_to_stdio_transport -v.

Architecture

This is a single Python package rooted at src/piwik_pro_mcp.
Main entrypoint and CLI wiring live in src/piwik_pro_mcp/server.py.
Public package layout is split mainly across api/, common/, tools/, assets/, and tests/ under src/piwik_pro_mcp/.
MCP tool registration is centralized in src/piwik_pro_mcp/tools/__init__.py; add new registrations there via the domain register_* function.
Environment-driven behavior is centralized in src/piwik_pro_mcp/common/settings.py.
Runtime schema discovery for JSON-style tool attributes is tools_parameters_get in src/piwik_pro_mcp/tools/parameters.py.

Configuration

Required env vars: PIWIK_PRO_HOST, PIWIK_PRO_CLIENT_ID, PIWIK_PRO_CLIENT_SECRET.
Optional env vars commonly affecting behavior: PIWIK_PRO_SAFE_MODE, PIWIK_PRO_TELEMETRY, PIWIK_PRO_TM_RESOURCE_CHECK, PIWIK_PRO_HTTP_ALLOWED_HOSTS, PIWIK_PRO_ALLOW_INSECURE_HOST.
.env files are supported via python-dotenv.

Behavioral Gotchas

Safe mode is on by default. filter_write_tools() removes any tool without annotations.readOnlyHint=True, so read-only tools must be annotated correctly or they disappear from the exposed server.
src/piwik_pro_mcp/tests/test_integration.py is the enforced inventory of registered tools. When adding or removing tools, update the READ_ONLY_TOOLS or WRITE_TOOLS lists there.
Settings helpers in common/settings.py use @cache. Tests that patch PIWIK_PRO_SAFE_MODE, PIWIK_PRO_TELEMETRY, PIWIK_PRO_TM_RESOURCE_CHECK, PIWIK_PRO_HTTP_ALLOWED_HOSTS, or PIWIK_PRO_ALLOW_INSECURE_HOST must clear caches before and after, following src/piwik_pro_mcp/tests/conftest.py, src/piwik_pro_mcp/tests/common/test_settings.py, and src/piwik_pro_mcp/tests/test_telemetry.py.
If a tool accepts free-form attributes, keep its tools_parameters_get schema path working and add or maintain the corresponding MCP tests under src/piwik_pro_mcp/tests/tools/.

Read the full file on GitHub · 44 lines

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.

1mo ago Changed · +22 tokens per session e111e3a1715e
2mo ago First seen · 44 lines · 828 tokens per session scan A 68323107f04a

Subscribe to this mod's changes

mcp AGENTS.md is an instructions file published in the GitHub repository PiwikPRO/mcp (7 stars, last pushed yesterday), licensed MIT. It adds 850 tokens to every session, about $0.0034 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 2026-08-31.

Analytics and metrics

mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcp AGENTS.mdPiwikPRO/mcp	Instructions file	7	yesterday	MIT	A	850	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

mcp: Instructions file for Codex