Mail (p-l-ta) MCP Server
@p-l-ta/mail-mcp
npm
v1.3.5
Source verified
Published by p-l-ta — publish provenance cryptographically ties this package to that repository. That is proof of origin, not an official vendor package.
MCP server exposing Mail.app to Claude and other MCP hosts
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 − 0 = 100. What the published surface and source actually contain:
The deterministic scan raised no scored threat in the surface it inspected — the threat score stayed at 100. Capability observations and advisory notes are recorded but never lower it.
2. Client adoption risk — 100 − 6 = 94. 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 |
|---|---|
| −6 | capability blast radius (high) — 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 7
high Shell/command execution in server code (dist/lib/applescript.js)MTC-SRC-002
In the server's implementation (`dist/lib/applescript.js:1`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: { execFile } from "node:child_process"; import { promisify } from "node:util"; import { writeFile, mkdtemp, rm } from "n
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/lib/applescript.js
high Shell/command execution in server code (dist/lib/envelope-index.js)MTC-SRC-002
In the server's implementation (`dist/lib/envelope-index.js:1`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: { execFile } from "node:child_process"; import { promisify } from "node:util"; import { readdir } from "node:fs/promises
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/lib/envelope-index.js
high Shell/command execution in server code (dist/lib/rules.js)MTC-SRC-002
In the server's implementation (`dist/lib/rules.js:8`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: { execFile } from "node:child_process"; import { promisify } from "node:util"; import { copyFile, readFile, writeFile, m
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/lib/rules.js
high Shell/command execution in server code (dist/lib/state.js)MTC-SRC-002
In the server's implementation (`dist/lib/state.js:8`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: { execFile } from "node:child_process"; import { promisify } from "node:util"; import { readFile, writeFile, mkdir } fro
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/lib/state.js
high Shell/command execution in server code (dist/tools/check_compatibility.js)MTC-SRC-002
In the server's implementation (`dist/tools/check_compatibility.js:2`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: { execFile } from "node:child_process"; import { promisify } from "node:util"; import { access } from "node:fs/promises"
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/tools/check_compatibility.js
high Shell/command execution in server code (dist/tools/submit_feedback.js)MTC-SRC-002
In the server's implementation (`dist/tools/submit_feedback.js:3`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: { execFile } from "node:child_process"; import { promisify } from "node:util"; import { getMacosVersion, getPackageVersi
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/tools/submit_feedback.js
medium Untrusted input can drive an external actionMTC-FLOW-005
Untrusted-input tools ([read_email, search_emails]) co-exist with external-action tools ([send_email]). A prompt injection could cause unwanted external actions, though no direct sensitive-data leak path was found.
Evidence: untrusted [read_email, search_emails] → sinks [send_email]
Fix: Require confirmation for state-changing/egress actions triggered after processing untrusted content.
Location: flow read_email → send_email
Tools 24
Each tool and what it can reach — statically extracted from the published source.
read_emailingests untrusted inputsearch_emailsingests untrusted inputsend_emailnetwork egressbulk_applyno sensitive capabilitybulk_flagno sensitive capabilitybulk_mark_readno sensitive capabilitybulk_moveno sensitive capabilitybulk_trashno sensitive capabilitycheck_compatibilityno sensitive capabilitycreate_mailboxno sensitive capability
Show 14 more tools ↓
create_ruleno sensitive capabilitydelete_ruleno sensitive capabilityempty_mailboxno sensitive capabilityget_unsubscribe_linkno sensitive capabilitylist_accounts_and_mailboxesno sensitive capabilitylist_recentno sensitive capabilitylist_rulesno sensitive capabilitylist_sendersno sensitive capabilitymove_emailno sensitive capabilityreply_to_emailno sensitive capabilityset_message_flagsno sensitive capabilitysubmit_feedbackno sensitive capabilitytrash_emailno sensitive capabilityupdate_ruleno 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 (24 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 |
|---|---|---|---|---|
v1.3.5 latest |
A 94/100 | 7 | 1.13.0 | 2026-09-07 |
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 @p-l-ta/mail-mcp --onlineOther implementations of Mail 7
Independent packages implementing the same tool, scanned with the same engine. Compare all 8 side by side →
MCP server for IMAP/SMTP email access with environment-based configuration
MCP server for interacting with Infomaniak Mail via web API
MCP server for the Orboto Mail Service — exposes send / batch / templates / suppression / inbound / webhooks / quota as MCP tools for Claude, Cursor, and other agent-aware clients. Boot via `npx @orboto/mail-mcp` with OMS_API_KEY in env.
MCP Server for SMTP and IMAP based email handling
High-performance MCP server for enterprise email management with trusted sender filtering, connection pooling, and intelligent caching
Connect your AI assistant to Superhuman Mail via MCP
More in Web, Search & Scraping
Agent IP: MCP server with patents search tools
MCP server for searching the Agent Almanac — the public catalog of 9,000+ Model Context Protocol servers. Find, install, and discover MCP servers from inside Claude Desktop, Cursor, Continue, Zed, or any MCP-aware agent.
Search agents & MCP servers by capability, with daily-observed pricing, liveness and market data.
Verified merchants accepting agentic payments on Lightning/L402/BOLT12/USDT — search, verify, pay.
Airframe MCP Client - Connect agents to Airframe's product intelligence
Amazon product search demand over time, with growth for any keyword. Free key at trendsmcp.ai