What is proton-mcp AGENTS.md?

Repository instructions for a Proton Mail MCP server, a program that lets AI agents interact with Proton Mail through a standard tool interface. They describe required documents, repository boundaries, validation, security, and approval rules for mailbox changes.

Use them before editing the server, its tool contracts, security-sensitive code, or changes that involve related deployment repositories.

They prevent changes from crossing into deployment repositories or bypassing checks for networking, credentials, and mailbox actions.

How purplehat93/proton-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to purplehat93/proton-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/purplehat93/proton-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/purplehat93/proton-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/purplehat93/proton-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/purplehat93/proton-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/purplehat93/proton-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/purplehat93/proton-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/purplehat93/proton-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/purplehat93/proton-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 469 This file is loaded in full into every session.

When invoked 469 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	$0.00469	$0.00469
Opus 5.5	$0.00188	$0.00188
Sonnet 5.5	$0.00094	$0.00094
Haiku 4.5	$0.00047	$0.00047

Measured 2mo ago against content hash 833a6bbf1602, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

proton-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 2mo 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 · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Keep this file short. Read the linked docs before changing architecture or behavior.

Before editing

Read ARCHITECTURE.md.
Read docs/SPEC.md for tool contracts.
Read SECURITY.md before touching networking, credentials, Bridge integration, or write actions.
Read docs/DEVELOPMENT.md for validation commands.
If the deployment repository nmousouros/nas-infrastructure is available in the same workspace, read its STATE.md and stacks/proton-mail/AGENTS.md for the current live deployment state. Do not copy changing runtime facts into this repository.

Repository boundary

This repository owns the MCP server implementation and its contracts. It does not own the live Synology deployment state or Proton Bridge image build.

Related repositories:

purplehat93/proton-bridge-docker — headless Proton Mail Bridge image.
nmousouros/nas-infrastructure — live Compose deployment and current runtime handoff.

When a task spans repositories, inspect the relevant source rather than inferring behavior from deployment documentation.

Rules

Controlled mailbox mutations require explicit user approval, bounded opaque ids, and the review/confirmation workflow. Do not add unattended mutation paths without an explicit safety design.
Never expose Proton Mail Bridge IMAP/SMTP ports to the LAN or internet.
Never commit Proton credentials, Bridge-generated credentials, tokens, keyrings, vault files, or mailbox data.
Never add a generic shell/command-execution MCP tool.
Prefer small, explicit MCP tools with bounded outputs.
Metadata-first: do not fetch or return full message bodies unless the caller explicitly requests a message.
Preserve existing tool schemas unless the task explicitly changes the contract.
Do not redesign the two-container architecture without an explicit request.
Runtime/deployment changes are not implied by source changes; do not assume permission to restart or modify the live NAS.

Validation

Before finishing a code change, run:

Read the full file on GitHub · 53 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.

2mo ago First seen · 53 lines · 469 tokens per session scan A 833a6bbf1602

Subscribe to this mod's changes

proton-mcp AGENTS.md is an instructions file published in the GitHub repository purplehat93/proton-mcp (0 stars, last pushed 8d ago), licensed MIT. It adds 469 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 2026-08-31.

proton-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
proton-mcp AGENTS.mdpurplehat93/proton-mcp	Instructions file	0	8d ago	MIT	A	469	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,685	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	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

proton-mcp: Instructions file for Codex