What is proton-mcp-server AGENTS.md?

Setup instructions for connecting AI agents to Proton Mail through Proton Mail Bridge, a desktop service that provides local mail access. The server is read-only and can list, search, and open messages from multiple configured Proton accounts.

Setting up and configuring the proton-mcp-server, then listing accounts, folders, and messages or searching and reading Proton Mail.

They provide prerequisites, installation steps, account configuration, and checks needed before an agent can read the mail.

How QinZinn/proton-mcp-server configures Codex and OpenCode

Reuse

Borrowing it

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

Clone the repo

git clone --depth 1 https://github.com/QinZinn/proton-mcp-server

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/qinzinn/proton-mcp-server/agents-md.svg)](https://agentmods.dev/instructions/qinzinn/proton-mcp-server/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/qinzinn/proton-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/qinzinn/proton-mcp-server/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 1,685 This file is loaded in full into every session.

When invoked 1,685 The same file — it is already loaded in full.

Security scan D 3 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	$0.01685	$0.01685
Opus 5	$0.00843	$0.00843
Sonnet 5	$0.00337	$0.00337
Haiku 4.5	$0.00169	$0.00169

Measured 7d ago against content hash 67103a8be172, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade D, and why

proton-mcp-server AGENTS.md scanned grade D with 3 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 7d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

passwords): `chmod 600 "$HOME/.config/proton-mcp/config.toml"`.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

`curl -LsSf https://astral.sh/uv/install.sh | sh` (Linux/macOS) — confirm

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

`curl -LsSf https://astral.sh/uv/install.sh | sh` (Linux/macOS) — confirm

AGENTS.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Setup guide for AI agents

This file is a runbook an AI agent (e.g. Hermes / opencode / Claude Code) can follow to install and configure the proton-mcp-server MCP server for a user. Execute the steps in order, verify at each checkpoint, and surface the final result to the user.

What this server does

Exposes a user's Proton Mail (read-only) to MCP-capable agents over the stdio transport, reading mail from the local Proton Mail Bridge IMAP server. Supports multiple Proton accounts, selected by name on each tool call. Read-only: list_accounts, list_folders, list_messages, search_messages, get_message.

Prerequisites (verify before starting)

Proton Mail Bridge is installed and running.
- Check: a TCP listener on 127.0.0.1:1143 (IMAP).
- Linux: ss -tlnp 2>/dev/null | grep -E '1143|1025'
- macOS: lsof -iTCP:1143 -sTCP:LISTEN
- If not running, tell the user to open the Bridge GUI and sign in. IMAP/SMTP must be enabled in Bridge settings.
Bridge credentials available. For each Proton account the user wants to connect, you need the bridge-generated password (shown in the Bridge GUI per account) — not the user's Proton login password — and the Proton address as the username. Security is STARTTLS on 127.0.0.1:1143.
Python 3.11+. Check: python3 --version.
uv (recommended installer). Check: uv --version. If missing, install: curl -LsSf https://astral.sh/uv/install.sh | sh (Linux/macOS) — confirm with the user before running an install script.

Install steps

git clone https://github.com/QinZinn/proton-mcp-server.git
cd proton-mcp-server
uv sync            # creates .venv and installs dependencies

The server binary is .venv/bin/proton-mcp-server (or uv run proton-mcp-server).

Configure accounts

Create the config at the default path (or a path you choose):

mkdir -p "${XDG_CONFIG_HOME:-$HOME/.config}/proton-mcp"

Then write $XDG_CONFIG_HOME/proton-mcp/config.toml (default ~/.config/proton-mcp/config.toml) — one [[accounts]] table per account:

Read the full file on GitHub · 145 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.

7d ago First seen · 145 lines · 1,685 tokens per session scan D 67103a8be172

Subscribe to this mod's changes

proton-mcp-server AGENTS.md is an instructions file published in the GitHub repository QinZinn/proton-mcp-server (0 stars, last pushed 1mo ago), licensed MIT. It adds 1,685 tokens to every session, about $0.0084 per session on Opus 5. A static security scan graded it D with 3 findings (asks for root, downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

proton-mcp-server: Instructions file for Codex