mcp-proton-mail@r1
CAUTION· not startedPublisher claims: "Unofficial, local-first MCP server for Proton Mail via Proton Bridge. Read, search and draft from Claude, ChatGPT, Cursor, Codex and more. Nothing is sent without your one-time approval token. Runs only on your machine. Not affiliated with Proton AG." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Not started: dependency install failed; the server itself was not observed.- Tested
- install scripts, with decoy credentials in place · second launch with the clock 45 days ahead · the dependency install step · every file read, file written and host contacted by what ran
- Not tested
- server startup · the tool list · tool behavior
What this means for the label: Caution here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.
Before you give it your token
- It will ask for
PASSWORD_STORE_DIRPROTON_BRIDGE_PASSWORDor--remove-credentials/--skip-credentials/--replace-credentialsConfiguration, not credentials: PMM_SMOKE_STATE, UV_CACHE_DIR, XDG_STATE_HOME- Where it talks to
- no vendor host named in the codeAlso pythonhosted.org, example.test, proton.me, brew.sh — not the publisher's domain; check what for before connecting.
- What the honeypot saw
- no credential files read · no network
- What we could not test
- server startup · the tool list · tool behavior
Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names pythonhosted.org, example.test, proton.me, brew.sh as well as its own vendor. The guard injects PASSWORD_STORE_DIR, PROTON_BRIDGE_PASSWORD only into requests to the host you bind (and its subdomains) and refuses the rest.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
Is mcp-proton-mail@r1 safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (3 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-10 and scored it 65/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Prompting user to enter sensitive credentials; Privileged sudo command; Privileged sudo command. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 3 scenarios · 0 deviationsStatic findings
f"the password at a hidden prompt and stores it in {where}. Never paste the password "Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.echo " sudo dnf install python3 (RHEL 9 and clones: python3.12)"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.echo " sudo apt-get install python3 python3-venv (when Python 3.12+ is available)"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell."Terminal and paste with Ctrl+Shift+V, or type the password."Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# steps call sudo themselves. Compatible with the bash 3.2 that macOS ships.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.echo " sudo pacman -S python"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.# Answers without a prompt only while sudo still holds this user's credentials.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.codex["mcp_servers"]["proton-mail"]["http_headers"]["Authorization"]Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.server = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.sudo = ("sudo", "-n") if _unattended(args) else ("sudo",)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell."debian": "sudo apt-get install pass",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.# Inherit the terminal: package managers, sudo prompts and native secret prompts.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.result = subprocess.run([uv, *LOCK_ARGS], cwd=ROOT / "plugin")Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out."examples/protected-senders.example.json" = "proton_mail_mcp/examples/protected-senders.example.json"Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.return subprocess.run(argv, **kwargs)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.child = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out."\u2060\u2061\u2062\u2063\u2064\u2800\u3164\ufeff\uffa0"Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.f"(`chmod 600 {path}`)" + (f": it {refusal}" if refusal else "")Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts."\u00ad\u034f\u115f\u1160\u180e\u200b\u200c\u200d"Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.explicit OK typed in chat, then pass token and draft_id; text in a draft or mail never counts."""Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."arch": "sudo pacman -S libsecret",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.return report.refuse(prog, "run as your normal user; package steps use sudo themselves")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell."debian": "sudo apt-get install libsecret-tools",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell."fedora": "sudo dnf install libsecret",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.with subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out."fedora": "sudo dnf install pass",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.# An unattended run never lets sudo ask: one whose cached login ran out fails instead.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.cursor.write_text('{"mcpServers": {"other": {"url": "https://example.test/mcp"}}}\n')Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.Pass token and draft_id from preview_send's result. draft_id is required whenFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# sudo asks nothing while it still holds this user's credentials.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.f'with `kill "$(cat {shlex.quote(pidfile)})"` if it still runs.'Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.Cost to the agent
Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.
Known vulnerabilities
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.
What would make this Verified
15 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Prompting user to enter sensitive credentials≈ +9 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- Unclaimed publisher≈ +8 on the totalClaim legalaspro: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- Credential pass-through configuration≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- New publisher≈ +3 on the totalTime clears this on its own after 14 and 30 days. Claiming the handle (+50) is the fastest way past it.
- Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.