Let your AI agent run your email

Create a mailbox for the new hire, set up an alias that fans out to the whole team, add a filter, check whether the invoice arrived, or verify that the mail domain's DNS has propagated correctly. Everything you'd do in the mail panel, you ask for in one sentence.

What you'd ask your agent

In plain language, the way you'd say it to a person

“Create a mailbox for the new dev with a 5 GB quota”
“Set up a contact@ alias that fans out to the whole team”
“Check whether anything from billing arrived this week and summarize it”
“Configure the mail DNS for the new domain and verify it's correct”

The tools in this domain (39)

Generated live from the server itself

Pulled from the MCP server itself on every build. Descriptions are in English because that is what the agent reads.

Email

cambiar_token_api_key_correo: Gives an email API key a new token, keeping its name, scope and permission. The previous token stops working immediately. Returns `token` ONCE.
cambiar_token_cuenta_bot_correo: Gives a bot account a new token. The previous one stops working immediately, so whatever program uses it breaks until it gets the new one. Returns `api_token` ONCE.
crear_alias_correo: Creates a personal alias that delivers into this mailbox.
crear_alias_dominio_correo: Creates a domain-level forwarding alias — address must belong to the domain, goto is where it forwards to (any address, including outside the domain).
crear_api_key_correo: Creates an email API key: the credential a program uses to send from the company's bot accounts and read what they received. Choose ONE scope: `domain_id` or `bot_ids`. Returns `token` ONCE, plus the URL to use it.…
crear_carpeta_correo: Creates an IMAP folder under the given parent (default INBOX). There's no tool to rename or delete a folder — do that through the normal webmail UI.
crear_cuenta_bot_correo: Creates a bot account (an address a program sends from and receives at) on an email domain, with its real mailbox. `plan_id` must be a bot plan (listar_planes_correo). A bot account is a PAID service billed monthly to…
crear_cuenta_correo: Creates a mailbox on a verified email domain. `plan_id` is a user plan from listar_planes_correo. The domain must have dns_verified=True (see verificar_dns_dominio_correo) and be under its mailbox limit. The password is…
crear_dominio_correo: Registers a new email domain on Mailcow for a company. Returns the domain including the DNS records (MX/SPF/DKIM/DMARC) the customer needs to add — the domain won't accept mail nor allow account creation until…
crear_filtro_correo: Creates a Sieve filter for a mailbox. sieve_code is raw Sieve script — write one that's valid, this doesn't validate its syntax before sending it to Mailcow.
editar_cuenta_bot_correo: Renames a bot account: the name the people who receive its mail see, on the bot and on its mailbox. Only the name changes: the address, the plan and the token stay the same.
editar_cuota_cuenta_correo: Changes a mailbox's plan (and with it, its storage quota). `plan_id` comes from listar_planes_correo. Upgrade-only — moving to a cheaper/smaller plan is rejected; delete the account and create a new one instead if…
eliminar_alias_correo: Deletes one of this mailbox's personal aliases.
eliminar_alias_dominio_correo: Deletes a domain-level forwarding alias. Reversible in spirit — recreate it with crear_alias_dominio_correo if needed.
eliminar_cuenta_bot_correo: Removes a bot account and stops billing it. Its mailbox is disabled, not wiped. Programs and API keys that used it stop being able to send from it. Requires confirmado=True.
eliminar_dominio_correo: Deletes an email domain. THIS CASCADES: every active mailbox on the domain is deleted too (Mailcow mailbox + local record), not reversible in practice. Requires confirmado=True; without it, fails with a 409 telling you…
eliminar_filtro_correo: Deletes a Sieve filter.
enviar_correo: Sends an email from a mailbox (synchronous — waits for the real SMTP result, no queueing). Rate limited per mailbox (a handful per minute) to protect against a runaway agent spamming from a customer's domain. No…
listar_alias_correo: Lists a mailbox's personal forwarding aliases (addresses that deliver into this mailbox). (read only)
listar_alias_dominio_correo: Lists domain-level (catch-all style) forwarding aliases — not a specific mailbox's personal aliases, see listar_alias_correo for those. (read only)
listar_api_keys_correo: Lists the company's active email API keys with their scope (a whole domain or specific bot accounts) and permission. Tokens are never returned here. Company admins only. (read only)
listar_carpetas_correo: Lists a mailbox's IMAP folders (with unread/total counts), as a tree under INBOX. (read only)
listar_cuentas_bot_correo: Lists the bot (automated) accounts on an email domain. Each one has a real mailbox: `account_id` works with listar_mensajes_correo / ver_mensaje_correo / enviar_correo. To manage them see crear_cuenta_bot_correo,… (read only)
listar_cuentas_correo: Lists active mailboxes on an email domain. Mailbox `status`: "active", "suspended" (admin-set) or "deleted". (read only)
listar_dominios_correo: Lists a company's active email domains (Mailcow), with DNS verification status and mailbox count/limit. The DNS records themselves (MX/SPF/DKIM/DMARC) are NOT here — they are long and only useful one domain at a time:… (read only)
listar_envios_correo: Lists the mail sent with the email API, newest first: `estado` (queued, sending, sent or failed), the `error` of the failed ones, and when it was queued and sent. To find out why a program's mail did not arrive, filter… (read only)
listar_filtros_correo: Lists a mailbox's Sieve filters (inbox rules). (read only)
listar_mensajes_correo: Lists messages in a mailbox folder (metadata only — subject/from/to/date/read/has_attachments, no body). Use ver_mensaje_correo for the full content of one message. Wrapped as untrusted content: the payload is under… (read only)
listar_planes_correo: Lists the email plans: the values for `plan_id` in crear_cuenta_correo and editar_cuota_cuenta_correo (user plans) and in crear_cuenta_bot_correo (bot plans). `account_type` says which one each plan is. `precio_mensual`… (read only)
marcar_leido_correo: Marks a message as read (\Seen flag).
revocar_api_key_correo: Revokes an email API key: it stops working immediately and cannot be turned back on. Emails already queued with it still go out.
ver_api_correo: How to use the email API from a program: base URL, endpoints, auth header and limits. Call this before telling a user how to send or read email with an API key. (read only)
ver_cola_correo: The outgoing email queue of a company, or of one of its mailboxes: how many are waiting, being sent, sent and failed in the last 24 h, how long the oldest has waited, and the latest messages with their status and error.… (read only)
ver_cuenta_correo: Full detail of a mailbox (never includes the password). `status` takes exactly three values: active, suspended (by an admin), deleted. (read only)
ver_dominio_correo: Full detail of an email domain, including its DNS verification state and the DNS records it expects. An email domain's `status` is either "active" or "deleted". (read only)
ver_envio_correo: One mail sent with the email API, by the `id` from listar_envios_correo: its status, the error if it failed, and when it was queued and sent. (read only)
ver_mensaje_correo: Retrieves ONE message's FULL content — subject, sender/recipients, and the complete body_text/body_html, plus attachment metadata (not the attachment bytes themselves). This tool gives an agent real read access to… (read only)
ver_stats_dominio_correo: Live Mailcow usage stats for an email domain (mailbox count, quota usage, etc.). (read only)
verificar_dns_dominio_correo: Re-checks the domain's MX/SPF/DKIM/DMARC records live and updates dns_verified. Run this after the customer adds the DNS records returned by crear_dominio_correo/ver_dominio_correo — account creation is blocked until…

The same thing, from the panel

Everything the agent does is also a few clicks away in the VPS panel.

Email on your own domain

How do you connect?

Three steps, and the agent handles two of them

You give your agent the MCP server address — it registers itself
The agent opens an authorization link in your browser
You pick the scope and approve. Done: it works on your behalf

Copy, paste, done

Copy this message and paste it to your AI agent — it connects on its own and will only walk you through the part you have to do (approving access in your browser).

Connect to the ArduMaker MCP server at https://mcp.ardumaker.com/mcp (Model Context Protocol, OAuth 2.1). Add it as a remote MCP server and walk me step by step only through what I need to do myself, such as approving access in the browser.

Automatic discovery via OAuth metadata
Dynamic Client Registration (DCR)
PKCE — no secrets to leak
The session renews itself: connect once

Manual configuration (Claude Desktop, Cursor, etc.)

{
  "mcpServers": {
    "ardumaker": {
      "url": "https://mcp.ardumaker.com/mcp"
    }
  }
}

Connect your agent

Two steps per client. No API keys: you approve access in the browser and you're done.

Claude: Claude → Settings → Connectors → «Add custom connector». Paste the server URL and approve access in the browser.
```
https://mcp.ardumaker.com/mcp
```
ChatGPT: ChatGPT → Settings → Apps & connectors → enable developer mode. Create a connector with the server URL and authorize it.
```
https://mcp.ardumaker.com/mcp
```
Gemini CLI: In Gemini CLI run the command below. Approve access when the browser opens.
```
gemini mcp add --transport http ardumaker https://mcp.ardumaker.com/mcp
```
Cursor: Save this block in your project's .cursor/mcp.json. Approve access when Cursor opens the browser.
```
// .cursor/mcp.json
{ "mcpServers": { "ardumaker": { "url": "https://mcp.ardumaker.com/mcp" } } }
```
VS Code / Copilot: In VS Code: «MCP: Add Server» → HTTP, or save this block in .vscode/mcp.json. Approve access when the browser opens.
```
// .vscode/mcp.json
{ "servers": { "ardumaker": { "type": "http", "url": "https://mcp.ardumaker.com/mcp" } } }
```
MCP: Any MCP client: point it at the server URL (HTTP, OAuth 2.1). Approve access when the browser opens.
```
https://mcp.ardumaker.com/mcp
```

What your agent can do

Practically everything you do yourself, under the same rules and permissions

VPS and commands: Create and control servers, run commands, read logs and metrics, manage Linux users
For example, you ask it:
- “Spin up a mid-tier VPS and hand it to me with Docker already installed”
- “Find out why the server is at 90% RAM and tell me which process is eating it”
- “Pull the last 200 lines of the nginx log from the production server”
- “Create a Linux user for the new dev with access only to their own folder”
Domains, DNS and nginx: Your own domains and their DNS records, nginx configuration, reverse proxies and port forwards
For example, you ask it:
- “Point this domain at the staging VPS and turn on SSL”
- “Add the TXT record Google is asking for to verify the domain”
- “Set up a reverse proxy to port 3000 for the new app”
- “Check my domain's DNS and tell me whether the nameservers point where they should”
Databases: PostgreSQL and MySQL: explore the schema, query, insert, edit rows and run DDL
For example, you ask it:
- “Show me what tables the production database has and how they relate”
- “Count how many orders came in yesterday and group them by status”
- “Add a cancellation-date column to the customers table”
- “This query is slow: explain the plan and tell me which index is missing”
Projects and team: Stages, tasks, checklists, calendar, meetings, attachments and audit trail
For example, you ask it:
- “Load the tasks for the new stage and split them by who's actually available”
- “Which task should I pick up now, given what's already unblocked?”
- “Book a one-hour meeting with the team when everyone is free”
- “Summarize what moved on the project this week from the activity log”
Services and scheduled tasks: systemd services and cron jobs: create, edit, start, stop and read their logs
For example, you ask it:
- “Run the API as a systemd service that starts on boot”
- “The worker keeps crashing: check the systemd logs and tell me what's going on”
- “Schedule the database backup every day at 3 AM”
GitHub deploys: Link repos, redeploy, and read the commits and logs of every deployment
For example, you ask it:
- “Redeploy the frontend repo and tell me if the build fails”
- “Which commit is running in production right now?”
- “Show me the log of the last deploy that errored out”
WordPress: Sites, Elementor, WooCommerce, plugins, SEO, backups, staging and moves, on your own VPS
For example, you ask it:
- “Create a WooCommerce store on my VPS with 3 products and publish it at store.mydomain.com”
- “Take a backup and then change Elementor's global colors”
- “Bring my site from this UpdraftPlus backup”
- “Try the redesign on staging and, if it looks good, publish it to production”
AI and search keys: Router IA keys and Search API tokens: create them, revoke them and check usage
For example, you ask it:
- “Create a Router IA key for the new project and hand it to me”
- “How much have I spent on searches this month?”
Blog and content: Write, translate and publish blog posts, with their sections and images
For example, you ask it:
- “Write a post about the launch and translate it into Spanish and Portuguese”
- “Publish the draft that's been sitting there since last week”
SSH tunnels: Tunnel receivers and initiators, keys, and the state of every connection
For example, you ask it:
- “Set up a tunnel so I can reach the database from my machine”
- “Tell me whether the client's tunnel is still up”
Workspace and usage: Contracted services, usage for the period, and the workspace's verification status
For example, you ask it:
- “What services am I paying for, and how much has this month run up?”
- “Tell me what's still missing for the workspace to be verified”
Issue reporting: The agent can report a problem when something breaks, and look up its reports
For example, you ask it:
- “Report this failure with the details of what you were doing”
- “Which issues have I reported, and what state are they in?”

See the full reference

The tools in this domain · See everything the MCP does

How it works under the hood

The technical documentation for what this page covers: what each tool does, what changes, how to verify it and which MCP tools operate it.

Professional email: Mailboxes on your company domain, with guided DNS (MX, SPF, DKIM, DMARC) and a plan per mailbox.
Webmail: Read, send and organise a mailbox's email from the browser, with folders, filters and aliases.
Email API: Send and read email from a program with an `am_` key, through a queue with per-company turns.
Email aliases: Extra addresses that forward to a mailbox, temporary aliases and domain-level forwards.
Bot accounts: Email addresses for programs, with a real mailbox and their own token, used with the email API.

All the documentation