MCP.Market

Agent Relay MCP server

by mmmikael·io.github.mmmikael/arelay·v0.2.0·10 stars
No reviews yet

End-to-end encrypted inbox where AI agents deliver files and request human approval.

B78/100grade B
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
B78/100

full report

Adoption
Growing

10 stars73 downloads/wk

Reviews

Write one

Nobody has reviewed Agent Relay yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Agent Relay tools (4, 2 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • deliver_to_inbox

    Deliver finished work (reports, files, artifacts) to the human's end-to-end encrypted Agent Relay inbox.

  • list_inbox_sessions

    List delivery sessions in the Agent Relay inbox (ids, timestamps, read state).

  • submit_email_draftwrite action

    Submit an outbound email draft to the Agent Relay inbox for human approval before it is sent

  • submit_spend_requestwrite action

    Propose a payment or purchase to the human's Agent Relay inbox for approval before any money moves

Public scan report

scanner v0.1.10 · 2026-11-04 · same rubric, same numbers if you re-run it

no findings
  • Code scan15 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitystatic API keys via environment variables6/15
  • Maintenancelast push 63 days ago12/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 78/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Agent Relay compares

Against every graded Email MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
78/100
higher than 62% of 915 Email servers
Tools
4
the typical Email server has 8
Tools that change things
50%
typical: 25%. Fewer write tools means less an agent can break
GitHub stars
10
more than 87% of 502 Email servers
Downloads a week
73
more than 40% of 270 Email servers with a package

What its tools let an agent do: 2 read · 2 change

Install Agent Relay in Claude Code, Cursor or VS Code

Runs npx -y @arelay/cli on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add arelay -- npx -y @arelay/cli
Add to Cursor

What the publisher says

From the Agent Relay repository's README, as published. We do not edit it. Read it on GitHub

Agent Relay

Agent Relay is where your AI agents ask permission. Agents draft emails, request spend, and deliver finished work into a private, end-to-end encrypted inbox; nothing leaves, sends, or charges until you approve it. Anything that can make HTTP requests can use it — Cursor, Codex, Claude Code, cron jobs, webhooks, or your own backend — and it is open source under MIT, so you can run it yourself.

An optional Email Review Relay plugin adds a human-in-the-loop outbound email path: agents submit encrypted drafts, you preview them in the same inbox, then approve or reject before anything is sent. It is enabled on arelay.app; self-hosters can turn it on with EMAILREVIEWRELAY_ENABLED=true (setup).

Two ways to use it:

(no deployment).

  • arelay.app — hosted service; sign up and connect your agents
  • Self-host — run this repo on your own infrastructure under the MIT license.

Contents

Using arelay.app

  • Get started
  • Connect your AI agent
  • Encryption (required)
  • Email Review Relay
  • Features

Self-hosting

  • Development setup
  • Environment variables
  • Deploy to production
  • Plugins
  • Tech stack

Reference

  • Contributing & help wanted
  • Security model
  • Terms of Service · Privacy Policy
  • Contributing
  • License

Using arelay.app

The hosted service at arelay.app handles deployment, database, storage, backups, TLS, and updates. The security model is the same as self-hosting: encrypted deliveries are decrypted in your browser, not on the server. The one exception is approving an email draft: the decrypted email is sent to the server in that request so it can be delivered, and is never stored as plaintext. Email itself is not end-to-end encrypted, so the recipient's mail provider sees the same content permanently.

Get started

Privacy Policy during signup (required on the hosted service).

  1. Open arelay.app and create an account with a passkey.
  2. Accept the Terms of Service and

or integration.

  1. Complete Set up encryption on first portal visit (passkey + recovery key).
  2. In the portal, open Account → Agent tokens and create a named token for each agent
  1. Copy the token once — it is shown only at creation time.
  2. Your inbox updates automatically when agents send deliveries (refresh every few seconds).

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Agent Relay: common questions

Is Agent Relay MCP server safe?
Mostly: it is graded B (78/100). Read the Agent Relay safety report
How do I install Agent Relay?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Agent Relay need an API key?
Yes. The registry entry asks for ARELAY_TOKEN.
Is Agent Relay maintained?
The last commit was 74 days ago (2026-09-02). The latest release is v0.2.0.
What can I use instead of Agent Relay?
Servers from other publishers that do the same job: Impri MCP server, Mailbuttons MCP server and Ads Uploader MCP server. Compare all Agent Relay alternatives.
How does Agent Relay compare with other Email MCP servers?
safety score 78/100 (higher than 62% of 915 Email servers); tools 4 (the typical Email server has 8); tools that change things 50% (typical: 25%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Agent Relay

Same job from other publishers: the closest match first, then the best rated.

All Agent Relay alternatives →
  • Impri
    Impri MCP server — human-in-the-loop approval inbox for AI agents
    A
  • Mailbuttons
    Governed email for AI agents: a sandbox inbox to read and send from, human approval to go external.
    A
  • Ads Uploader
    Meta Ads MCP: analyze, edit and bulk launch Meta ads, with an Agent Inbox for approvals.
    A
  • Clize
    Real-world actions for AI coding agents: an inbox with approval outbox, deploys, domains, payments.
    A
  • Inbox Zero
    Search Gmail and Outlook, save drafts, manage email rules, and view email stats.
    A