mcpField
M
Mailows

Mailows

Remote
mailows.comCommunication0Updated 4w ago
RepositoryVisit website

About Mailows

Mailows is a hosted email service for AI agents, giving each agent a dedicated address on a domain rather than sharing a human inbox. Inbox access is controlled through grants that can be revoked independently.

Key features

  1. 01Dedicated email inboxes for agents
  2. 02List, read, and send email
  3. 03Scoped, revocable access grants
  4. 04OAuth authorization with PKCE

Use cases

  1. 01Give an agent its own domain email address
  2. 02Limit which inboxes an agent can access

MCP support

Mailows provides a hosted remote MCP server at `https://mcp.mailows.com/mcp` for Grok Build and other MCP clients. It uses OAuth authorization, with tokens stored by the MCP client.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://mcp.mailows.com/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

Mailows for Grok

Remote MCP plugin that connects Grok Build to the hosted Mailows server at https://mcp.mailows.com/mcp.

Mailows gives AI agents their own real email inboxes — not a shared human mailbox. Each agent gets a dedicated address on your domain; you decide which inboxes it may touch and can revoke grants independently.

Install

Once listed in the xAI plugin marketplace:

grok plugin install mailows --trust

Or add the remote server directly:

grok mcp add --transport http mailows https://mcp.mailows.com/mcp

First use triggers an OAuth browser flow (authorization code + PKCE). Tokens stay in the MCP client credential store.

Docs

Operator: DW Technology LLC.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.