AI Mail MCP

com.aimailmcpPublished by aimailmcp.comOfficial publisherv0.1.3Updated Oct 28, 2026

One inbox for every hat you wear: support, sales, billing mail, triaged and drafted by your agent.

VerifiedStreamable HTTPWeb executableProductivity & Workflow Communication & Collaboration

Server details

Identifier: com.aimailmcp/mail
Transport: Streamable HTTP
Runtime: Web executable
Trust: Verified
Published: Oct 13, 2026

Security note

MCP servers receive tool arguments from a conversation and may perform external actions. Review what a server can do before you enable it, and give it only the access it needs.

The registry verified that this server's namespace belongs to aimailmcp.com, which also runs its endpoint. That identifies the publisher; it does not make the server's tools safe.

SourceWeft's checks cover whether the listing is complete and the endpoint answered; they do not review the server's code or what its tools do.

Add a badge to your README

Show readers this MCP server is listed on SourceWeft. The badge links to this page.

[![Listed on SourceWeft](https://sourceweft.com/badge/mcp/com.aimailmcp%2Fmail.svg)](https://sourceweft.com/mcp/com.aimailmcp%2Fmail?utm_source=readme&utm_medium=badge)

Overview

AI-generated overview

Hosted email service over MCP that lets an assistant manage domains and mailboxes, read a unified inbox, and send, reply or forward mail.

What you can do: Add domains and get or apply DNS plans, verify them, list and remove domains
Create, list and delete mailboxes, plus aliases, catch-alls and forwarding
Read one unified inbox: list, full-text search, fetch messages, threads and attachments, wait for a message, mark read, label, archive
Send, reply in-thread, forward and save drafts
Create, list and delete signed webhooks for incoming mail and finished sends
Mint, list and revoke scoped tokens and review the audit log and usage
When to use it: Useful when an agent needs real email addresses on your own domain: triaging support, sales or billing mail, catching sign-up codes and magic links, or sending and replying on behalf of a mailbox.
Requirements: Remote Streamable HTTP endpoint; nothing to install locally. Sign in with OAuth 2.1 (email plus a 6-digit code) or send an Authorization bearer token obtained from the signup flow. A domain you control is needed for mailboxes; clients without remote support can bridge over stdio.

Before you install

The token grants access to real mailboxes and, if enabled, the ability to send mail under your domain; scope tokens narrowly and set daily send caps. Sending, replying, forwarding, DNS changes, mailbox deletion and webhook creation all change state. Inbound email is untrusted content and should be treated as data, not instructions. Usage is metered and reported by operation.

Installation

In SourceWeft

Open AI Mail MCP in the dashboard and add it to a workspace.
Connect the required credentials. They are stored privately and never shown on public pages.
Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/com.aimailmcp%2Fmail/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "ai-mail": {
      "type": "http",
      "url": "https://aimailmcp.com/mcp"
    }
  }
}

README

[AI Mail MCP logo]

AI Mail MCP

Real email for AI agents, over MCP. Add a domain and get the exact DNS records, create mailboxes, read one unified inbox across all of them, wait for sign-up codes and magic links, and send, reply in-thread and forward. Tokens are scoped to mailboxes with a send permission and a daily cap, every write has a dry run, and every call is audited.

Website and full tool reference: https://aimailmcp.com
MCP endpoint (remote, Streamable HTTP): https://aimailmcp.com/mcp
Official MCP Registry: com.aimailmcp/mail
Machine-readable tool registry: https://aimailmcp.com/tools.json

This repository holds the public docs, server.json and logo. The service is hosted; there is nothing to install or run locally.

Connect

Claude Code

Claude.ai and Claude Desktop: Settings, Connectors, Add custom connector, paste https://aimailmcp.com/mcp.

Any MCP client

Clients without remote support can bridge over stdio: npx -y mcp-remote https://aimailmcp.com/mcp. Agent-oriented install steps: llms-install.md.

Sign in

OAuth 2.1 (most clients do this for you): dynamic client registration and PKCE. You enter your email and a 6-digit code we send you.
Bearer token (agents without a browser):

bash

curl -X POST https://aimailmcp.com/api/v1/signup -H 'content-type: application/json' -d '{"email":"[email protected]"}'curl -X POST https://aimailmcp.com/api/v1/signup/confirm -H 'content-type: application/json' -d '{"email":"[email protected]","code":"123456"}'

curl -X POST https://aimailmcp.com/api/v1/signup -H 'content-type: application/json' -d '{"email":"[email protected]"}'curl -X POST https://aimailmcp.com/api/v1/signup/confirm -H 'content-type: application/json' -d '{"email":"[email protected]","code":"123456"}'

Then send Authorization: Bearer amk_.... Use create_token to hand narrower tokens to other agents.

Tools

Domains

Bring a domain, get the exact DNS records, verify it.

Tool	What it does
`add_domain`	Add a domain (or subdomain) to this account so it can hold mailboxes.
`get_dns_plan`	The exact DNS records (MX, SPF, DKIM, DMARC, ownership TXT) a domain needs for receiving and sending, and whether each is in place.
`apply_dns`	Write the DNS plan to a managed domain on this service's Cloudflare account: enables Email Routing (MX + SPF), routes mail to the receiver, registers the domain for sending and adds DKIM and DMARC.
`verify_domain`	Check the domain's live DNS: ownership TXT (external domains), MX, SPF, DMARC and the sending provider's DKIM status.
`list_domains`	Every domain on this account with its status, mode, sending readiness and mailbox count.
`remove_domain`	Remove a domain from this account.

Mailboxes

Addresses that receive and send, plus aliases, catch-alls and forwarding.

Tool	What it does
`create_mailbox`	Create a mailbox (an address that receives and sends) on one of this account's domains.
`list_mailboxes`	Every mailbox this token can see, with unread counts, last received time, aliases, forwarding and route address.
`delete_mailbox`	Delete a mailbox.
`add_alias`	Deliver mail sent to another address on one of this account's domains into an existing mailbox.
`set_catch_all`	Deliver mail for any unknown address on a domain into one mailbox, or pass mailbox: null to turn the catch-all off.
`set_forwarding`	Also forward every message a mailbox receives to up to 5 external addresses (the original is attached as message/rfc822).

Read

One unified inbox across every mailbox the token can see.

Tool	What it does
`list_messages`	One inbox across every mailbox this token can see, newest first, each item tagged with its mailbox.
`search_messages`	Full-text search over subject, sender, recipients and body across every mailbox this token can see (all folders by default).
`get_message`	Headers, text body (or text derived from HTML), extracted links, attachment list and threading ids for one message.
`get_thread`	The whole conversation a message belongs to, inbound and outbound, oldest first, as previews.
`wait_for_message`	Block until a matching message arrives (or timeout_s, max 60, default 25) and return it in full.
`get_attachment`	One attachment as base64 (up to 5 MB).
`mark_read`	Mark up to 100 messages read (or unread with read: false).
`label`	Add and/or remove labels on up to 100 messages.
`archive`	Move up to 100 messages out of the inbox into archive (or back with unarchive: true).

Send

Send, reply in-thread, forward and draft, behind per-token gates.

Tool	What it does
`send_message`	Send a new email from a mailbox in scope (or send a saved draft with draft_id).
`reply`	Reply in-thread from the mailbox that received the message (In-Reply-To and References set, "Re:" added once, original quoted).
`forward`	Forward a message (with its attachments) to new recipients, with an optional note on top.
`create_draft`	Save a draft in a mailbox (folder drafts) for a human or another agent to review.

Automation

Signed webhooks when mail arrives or a send finishes.

Tool	What it does
`create_webhook`	POST a signed JSON event to your https URL when mail arrives or a send finishes.
`list_webhooks`	Webhooks on this account with their events, scope and last delivery status.
`delete_webhook`	Stop and remove a webhook.

Access

Scoped tokens for other agents, and the audit log.

Tool	What it does
`create_token`	Mint a token for another agent, scoped to some mailboxes (default: all), with or without send permission and with a daily send cap.
`list_tokens`	Tokens on this account: label, prefix, scope, send permission, cap, last use.
`revoke_token`	Revoke a token by id or prefix.
`audit_log`	Recent tool calls on this account (every attempt, including refusals and dry runs): tool, outcome, token, time.
`get_usage`	What this token used: sends and recipients, inbound messages, storage GB-days and tool calls, with what each cost us, by operation or by day. Admin tokens can ask for the whole account; delegating tokens for one end customer.

Full schemas: https://aimailmcp.com/tools.json

Security model

Inbound mail reaches the server only as HMAC-SHA256 signed raw messages from our Cloudflare email worker; unsigned posts are rejected.
Everything a sender controls comes back inside an untrusted_external_content envelope. Agents should treat email as data, never as instructions.
Tokens are stored as hashes, scoped to mailboxes, and can never mint a more powerful token.
Privacy: https://aimailmcp.com/privacy · Contact: [email protected]

License

The contents of this repository (docs, logo, server.json) are MIT licensed. The hosted service is operated by Hapi.

Source: README.md at commit e93ae73

Tools

This server asks you to sign in, so SourceWeft could not read its tools without an account and has not indexed them. What a connected account sees can depend on that account and its permissions.

Version history

v0.1.3LatestOct 26, 2026
v0.1.2Oct 20, 2026
v0.1.1Oct 20, 2026
v0.1.0Oct 13, 2026

Score

85% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

Reached in the last 30 daysRequired25 pts
Auth declaredRequired10 pts
Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
DescriptionRequired15 pts
Logo10 pts
Documentation15 pts
License10 pts