radmail-mcp by radmail.ai
MCP server · Email delivery APIs · indexed, not reviewed
HostedLocalvendor's own
Not reviewed
No score, grade or rank. This listing is facts from the official MCP registry and our own checks, and it stays out of the rankings until the panel reviews it.
Email OS for agents - real-inbox search, triage, commitments, and a verifiable BEC hard-stop.
Facts
- MCP registry
ai.radmail/radmail-mcp· 0.5.0- Endpoint
https://radmail.ai/api/mcp/sandbox- Packages
npmradmail-mcp stdio- Website
- radmail.ai/for-agents
- npm / week
- 108
- GitHub stars
- 0
- Registry entry
- updated 17 Aug 2026
From the official MCP registry, the package registries and our own checks. JSON · Markdown
Why it's listed
- It's published in the registry under radmail.ai, a namespace the registry only gives to whoever proves they control that domain.
Being indexed says nothing about quality, and nobody can pay for it. Is this yours? Ask for a review.
Tools it lists 6 · about 604 tokens of context · checked 16 minutes ago
| Tool | What it does | Hint |
|---|---|---|
triage_inbox | Rank a mailbox on two axes (importance x urgency) and return what needs a human now versus what can wait or is already handled — with each thread's open commitment (the promise you owe or are owed, and whether it's… | |
list_right_now | Return only the 'Right Now' lane — the most recent and most important messages that genuinely can't be missed. | |
why_surfaced | Explain in plain English why a given message was surfaced — the signals (sender, urgency, commitment) behind its rank. | |
list_commitments | Extract the open commitments in the correspondence, both owed by you and owed to you, with who and by-when. | |
draft_reply | Draft a reply for a thread. It returns text for a human to review — it does not and cannot send it. | |
search | Find a specific message by sender, subject, or content. Results come back most-relevant + newest first, and every hit says where it matched (from / subject / body) and why. On this hosted sandbox it searches the… |
What https://radmail.ai/api/mcp/sandbox answered to tools/list, asked without credentials. answered without the initialize handshake. The token figure is the size of the list as sent, divided by four; a model sees about that much before it calls anything. Full definitions, input schemas included, are in the listing's JSON under mcpTools.
How its tools read to an agent 0 errors · 6 warnings · 1 note
- warnTC16draft_replyno readOnlyHint or destructiveHint
- warnTC16list_commitmentsno readOnlyHint or destructiveHint
- warnTC16list_right_nowno readOnlyHint or destructiveHint
- warnTC16searchno readOnlyHint or destructiveHint
- warnTC16triage_inboxno readOnlyHint or destructiveHint
- warnTC16why_surfacedno readOnlyHint or destructiveHint
- noteTC24server6 of 6 tools have no outputSchema
The checks from /check and anchor check, run each day on the list above: about 604 tokens of definitions. Not part of the score yet. Check your own server.