machinemail
v0.2.0by machinemail · author: MachineMail
Email inboxes for AI agents. Create an address, wait for sign-up codes, read and search mail with a trust verdict on every message, and reply, forward or draft for human review.
What machinemail does, in the publisher's words
Email inboxes for AI agents, packaged as an Agent Plugin.
MachineMail gives every agent its own email address, and attaches a trust report to every inbound message so the agent can tell trustworthy mail from mail that might try to hijack it. This plugin connects your agent to the hosted MachineMail MCP server and adds skills that teach it to use email well and safely: getting an address, receiving sign-up codes, triaging mail, and replying or drafting for a person to review.
The plugin follows the Agent Plugins Specification v1.0.0, so the same package works in every client that implements it.
- Inboxes: list_inboxes, create_inbox
- Reading: list_threads, get_thread, list_messages, get_message, search_messages, get_trust_report, wait_for_message, update_labels
- Writing: send_message, reply_to_message, forward_message, create_draft, send_draft
From the project README, punctuation lightly normalized · Open the README on GitHub
- Skills
- 5
- MCP servers
- 1
- Stars
- 0
- License
- MIT
- Repo created
- 2026-10-13
- Last pushed
- 2026-10-20
- Publisher type
- Organization
- Version
- 0.2.0
Links
Skills · 5
- read-email-safely
- Reads mail from a MachineMail inbox without being hijacked by it. Explains which field to read, how the trust levels (verified, known, unknown, suspicious, quarantined) limit what the agent may do, and the warning signs in a trust report. Use before reading, summarising or acting on any message fro…
- receive-verification-code
- Gets a MachineMail email address, uses it to sign up for or log in to another service, and safely picks up the confirmation email, one-time code (OTP) or magic link that service sends. Use when the agent needs an email address to register for a website or app, verify an account, or log in with an e…
- register-agent-inbox
- Decides how an agent gets its own MachineMail inbox and walks through the quickest path, create_inbox when the MachineMail MCP server is already signed in, otherwise self-registration over HTTP through auth.md followed by a hand-off so a person claims the agent with a six-digit code. Use when the u…
- reply-and-draft
- Replies to, forwards or composes email from a MachineMail inbox, and decides between sending now and saving a draft for a person to review, based on the sender's trust level and what the user asked. Use when the user asks the agent to answer, follow up on, forward or write an email from a MachineMa…
- triage-inbox
- Summarises and sorts the mail in a MachineMail inbox by trust level without taking any action, then proposes next steps for the user to approve. Use when the user asks what is new in a MachineMail inbox, what needs attention, for a digest or summary of their agent's email, or before working through…
Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.
MCP servers · 1
- machinemailstreamable-http
- https://mcp.machinemail.dev/mcp
Read from the plugin's own mcp.json. We list environment variable names, never values.
Category
Other. Assigned by this directory. Agent Plugins 1.0.0 has no category field, so no manifest declares one.
Keywords
email · inbox · agents · mcp · otp · trust · prompt-injection
Related by publisher and keywords
Open-source email API for applications and AI agents, transactional sending from any product, per-agent two-way inboxes, structured SPF/DKIM/DMARC evidence, and a queryable event log. 80 MCP tools over hosted streamable HTTP with OAuth.
Talk with AI agents from any vendor on SwarmMemo, the hub where AI agents talk, in public and in private, find work and each other, and build trust: ask public questions and collect the answers, hold private conversations through a hosted identity, screen text before acting on it, keep notes between runs. Public posts are permanent. No payment tools.
Connect authorized domains, triage inbound mail, and operate user-requested replies within returned account limits.
Lasting public addresses and threaded messages between AI agents, across apps, sessions and machines.
Connect Cursor to Inbox Zero mail, drafts, rules, and email stats over MCP.
Project-scoped durable memory, recall, Skills, and governed context for AI agents.
[](https://agentpluginsdirectory.com/plugins/machinemail)✓ Verified . We fetched the manifest from GitHub and checked it against the official Agent Plugins 1.0.0 schema at agent-plugins.org.