Mailwarden MCP server
io.github.csitte/mailwarden·v0.27.2Gmail MCP server for email triage: search, labels, archive, trash, unsubscribe, snooze.
not scanned yet
0 stars129 downloads/wk
Reviews
Write oneNobody has reviewed Mailwarden yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Mailwarden tools
No tool declarations could be read from the package source. They show once the server is installed.
How Mailwarden compares
Against every graded Email MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 92/100
- higher than 90% of 916 Email servers
- Downloads a week
- 129
- more than 64% of 235 Email servers with a package
Release history: 9 versions in the registry since 2026-09-14, latest 2026-11-03, typically one every 3 days.
Install Mailwarden in Claude Code, Cursor or VS Code
Runs npx -y mailwarden on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add mailwarden -- npx -y mailwarden
What the publisher says
From the Mailwarden repository's README, as published. We do not edit it. Read it on GitHub
mailwarden
A reliable, native Gmail MCP server — full mailbox triage for AI assistants, with the feature no other Gmail MCP server ships: mailbox-side snooze.
Highlights
resurface in the inbox on a date. Built on dated labels + a sweep, so it works from any client, is visible in Gmail itself, and survives restarts. (Where another server offers a "snooze", it is a local reminder list — the mail never leaves or re-enters the inbox.)
- Snooze — the only mailbox-side snooze in a Gmail MCP server. Archive a thread now, have it
answer is:unread from a stale thread-level read state: measured in one real mailbox, 86% of the threads it returned held no unread message at all; in a second mailbox, no drift whatsoever. You cannot tell which mailbox you are in without looking, so search re-verifies every hit against its live labels. Paginated via pageToken/nextPageToken. (the measurements)
- Search you can trust. Gmail's threads.list — the call any thread search goes through — can
the receiving server recorded, so "is this really from my bank?" is answered from the message's own headers instead of from how the domain looks. It reads the receiving server's report only — a message can carry forged ones of its own — and says unchecked when nobody checked, because a missing check is not a passing one.
- Sender authentication, not sender spelling. get_thread reports the SPF/DKIM/DMARC results
1000 messages per API request — with per-chunk partial-success reporting instead of all-or-nothing. The snooze sweep uses the same batch path.
- Bulk operations that scale. bulk_modify archives/labels everything matching a query at
structuredContent alongside fenced JSON text — no parsing guesswork for clients. Failures are structured as well: a code and a retryable flag, so a client can tell "try again later" from "re-authorize" without reading prose.
- Structured outputs. Every tool declares an outputSchema and returns validated
optional read-only mode, no telemetry, no open ports by default, symlink-safe download fencing, injection-fenced output. And no code path that could send: every Gmail request passes an egress checkpoint that refuses messages.send, every draft endpoint, permanent deletion and forwarding settings, whatever a compromised or careless caller asks for. One deliberate exception: unsubscribe / bulk_unsubscribe (manage tier) contact the opt-out endpoint named in a message's own header — the only non-Google host mailwarden ever reaches, and a read-tier deployment makes no outbound request at all. Details under Security & privacy and Unsubscribing.
- Small attack surface. No send tools (no exfiltration path for prompt-injected mail),
bodies decoded in their declared charset (no mojibake for ISO-8859-1/Shift_JIS mail), 429/5xx retried with exponential backoff.
- Correct with real-world mail. RFC 2047 headers decoded (=?UTF-8?B?…?= → readable text),
Why
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Mailwarden: common questions
- Is Mailwarden MCP server safe?
- Yes, by our scan: it is graded A (92/100). Read the Mailwarden safety report
- How do I install Mailwarden?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Mailwarden need an API key?
- No secret keys are declared. It reads 4 settings from the environment.
- Is Mailwarden maintained?
- The last commit was 40 days ago (2026-09-25). The latest release is v0.27.2.
- What can I use instead of Mailwarden?
- Servers from other publishers that do the same job: Mailoo - Email MCP Server, MCPEmails MCP server and Gmail MCP server. Compare all Mailwarden alternatives.
- How does Mailwarden compare with other Email MCP servers?
- safety score 92/100 (higher than 90% of 916 Email servers); downloads a week 129 (more than 64% of 235 Email servers with a package). Full comparison.
Alternatives to Mailwarden
Same job from other publishers: the closest match first, then the best rated.
- Mailoo - Email MCP ServerEmail MCP server for AI agents: IMAP/SMTP, Gmail, Outlook, calendar, ManageSieve, AI triage, OAuth2.5.0(1)GrowingA
- MCPEmailsNever-stored live email: read, send and triage Gmail, Outlook / Microsoft 365, or any IMAP mailbox.not reviewedGrowingA
- GmailAllow AI systems to read, send, archive, and manage emails via Gmail.not reviewedGrowingB
- MailboxMulti-account email MCP server for Gmail, IMAP, and JMAP: search, send, drafts, labels.not reviewedGrowingB
Inbox ZeroSearch Gmail and Outlook, save drafts, manage email rules, and view email stats.not reviewedEstablishedA