A local connector for Proton Mail that lets an agent prepare drafts and stage attachments without sending messages. It runs from a Python package and is designed to work with different agent clients.

Preparing Proton Mail drafts and handling attachments before review. It also provides limits and temporary storage settings for draft and upload data.

It keeps email preparation local and draft-only, reducing the risk of sending a message or exposing an attachment by mistake.

proton-safe — MCP server by fbossiere/proton-safe-mcp

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.

Clone the repo

git clone --depth 1 https://github.com/fbossiere/proton-safe-mcp

Made for: Claude Code, Codex, Cursor, Gemini CLI, 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/mcp/fbossiere/proton-safe-mcp/proton-safe-proton-safe/github.svg)](https://agentmods.dev/mcp/fbossiere/proton-safe-mcp/proton-safe-proton-safe)

Your own site

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

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

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

Socket warn 30 Oct 2026

How audits are shown

Origin original No closer match found in the catalogue.

Security

Grade A, and why

proton-safe 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 12d 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.

plugins/proton-safe/.mcp.json · 28 lines

What it actually says

{
  "proton-safe": {
    "command": "uvx",
    "args": [
      "--from",
      "proton-safe-mcp==2.3.2",
      "proton-safe-mcp",
      "serve"
    ],
    "env_vars": [
      "DBUS_SESSION_BUS_ADDRESS",
      "HOME",
      "PATH",
      "PROTON_BRIDGE_ALIASES",
      "PROTON_BRIDGE_USER",
      "PROTON_IMAP_PORT",
      "PROTON_MCP_MAX_ATTACHMENT_BYTES",
      "PROTON_MCP_MAX_RECEIVED_ATTACHMENT_BYTES",
      "PROTON_MCP_MAX_BODY_CHARS",
      "PROTON_MCP_MAX_CHUNK_BYTES",
      "PROTON_MCP_STATE_DIR",
      "PROTON_MCP_UPLOAD_TTL_SECONDS",
      "XDG_RUNTIME_DIR"
    ],
    "startup_timeout_sec": 30,
    "tool_timeout_sec": 120
  }
}

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.

12d ago Changed 1d3ce0f918df
27d ago Changed af2d29f3f3f7
1mo ago Changed cacc2695c262
1mo ago Changed 3493afcb03b6
1mo ago Changed f3a94b696f2d
2mo ago Changed b337b96dfd54
2mo ago Changed · +1 lines 4f881ac6b714
2mo ago First seen · 27 lines scan A a697e7aca334

Subscribe to this mod's changes

proton-safe is an MCP server published in the GitHub repository fbossiere/proton-safe-mcp (6 stars, last pushed 4d ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. 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.

email fastmcp human-in-the-loop imap linux mcp

proton-safe next to 6 mcp servers from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
proton-safefbossiere/proton-safe-mcp	MCP server	6	4d ago	MIT	A	—	Claude Code, Codex, Cursor, Gemini CLI, OpenCode
email-devWh1isper/mcp-email-server	MCP server	391	yesterday	BSD-3-Clause	A	—	Claude Code, Codex, Cursor, Gemini CLI, OpenCode
mcpagenticmail/agenticmail	MCP server	251	10d ago	MIT	A	—	Claude Code, Codex, Cursor, Gemini CLI, OpenCode
e2atokencanopy/e2a	MCP server	199	2d ago	Apache-2.0	A	—	Claude Code
mcp-servertokencanopy/e2a	MCP server	199	2d ago	Apache-2.0	A	—	Claude Code, Codex, Cursor, Gemini CLI, OpenCode
imap-mcp-servernikolausm/imap-mcp-server	MCP server	129	2d ago	MIT	A	—	Claude Code, Codex, Cursor, Gemini CLI, OpenCode
thunderbird-clivitalio-sh/thunderbird-cli	MCP server	69	7d ago	MIT	A	—	Claude Code, Codex, Cursor, Gemini CLI, OpenCode