Proton Mail MCP Server
proton-mail-mcp
npm
v1.0.2
Source verified
Published by sethbang — publish provenance cryptographically ties this package to that repository. That is proof of origin, not an official vendor package.
Unofficial MCP server for Proton Mail (not affiliated with Proton AG) — send, read, search, and organize email over SMTP and IMAP
The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.
1. Threat score — 100 − 1.2 = 99. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −1.2 | Instruction-override directive MTC-INJ-AUTH-2 | injection |
2. Client adoption risk — 99 − 3 = 96. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:
| Points | Adoption-risk factor |
|---|---|
| −3 | capability blast radius (moderate) — client exposure if the model is manipulated |
Capability observations and info notes are shown under Findings but never scored.
Open any row's finding below for the file, line and evidence behind a deduction.
Findings 2
medium Untrusted input can drive an external actionMTC-FLOW-005
Untrusted-input tools ([forward_email, read_message, list_attachments, download_attachment, mark_all_read]) co-exist with external-action tools ([send_email, reply_email, forward_email]). A prompt injection could cause unwanted external actions, though no direct sensitive-data leak path was found.
Evidence: untrusted [forward_email, read_message, list_attachments, download_attachment, mark_all_read] → sinks [send_email, reply_email, forward_email]
Fix: Require confirmation for state-changing/egress actions triggered after processing untrusted content.
Location: flow forward_email → send_email
low Instruction-override directiveMTC-INJ-AUTH-2
Instruction-override directive detected in the description of tool "read_message". Instruction-like content in tool metadata is executed by the model, not the human, and is the primary tool-poisoning vector.
Evidence: ignore previous instructions
Fix: Tool descriptions should describe behavior, not instruct the assistant. Treat imperative / secrecy / sequencing language in metadata as hostile.
Location: tool read_message · description
Tools 32
Each tool and what it can reach — statically extracted from the published source.
forward_emailingests untrusted inputnetwork egressdownload_attachmentingests untrusted inputlist_attachmentsingests untrusted inputmark_all_readingests untrusted inputread_messageingests untrusted inputreply_emailnetwork egresssend_emailnetwork egressbulk_deleteno sensitive capabilitybulk_moveno sensitive capabilitybulk_update_flagsno sensitive capability
Show 22 more tools ↓
bulk_update_labelsno sensitive capabilitycount_messagesno sensitive capabilitycreate_folderno sensitive capabilitycreate_labelno sensitive capabilitydelete_folderno sensitive capabilitydelete_messageno sensitive capabilitydelete_threadno sensitive capabilityempty_folderno sensitive capabilityflag_threadno sensitive capabilityfolder_statsno sensitive capabilityget_threadno sensitive capabilitylist_foldersno sensitive capabilitylist_messagesno sensitive capabilitymove_messageno sensitive capabilitymove_threadno sensitive capabilityrename_folderno sensitive capabilityreply_all_emailno sensitive capabilitysave_draftno sensitive capabilitysearch_messagesno sensitive capabilitytop_sendersno sensitive capabilityupdate_message_flagsno sensitive capabilityupdate_message_labelsno sensitive capability
Toxic flows 1
Cross-tool combinations that form a data-exfiltration primitive (untrusted input → sensitive source → external sink).
What this scan could not see
- Tools were statically extracted from the published source (32 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Versions 1
Scan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v1.0.2 latest |
A 96/100 | 2 | 1.13.0 | 2026-09-08 |
Embed this score
Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.
Verify this score yourself
The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.
npx mcptrustchecker scan proton-mail-mcp --onlineMore in Other
A Model Context Protocol server implementation for AdGuard Home that enables AI agents to query and manage DNS records, filtering rules and more
Identity oracle and trust layer for autonomous AI agents. Bidirectional KYA and trust scoring.
MCP server with Airtable integration
A free one-minute reset for people, delivered by AI, with no account or personal data.
Access SEC filings efficiently, save time and tokens, and get cited answers.
A smart [MCP](https://modelcontextprotocol.io) server for [AniList](https://anilist.co) that gets your anime/manga taste - not just API calls.