MCP ServerHTTPOfficialv1.0.0

Smithery Agentmail MCP Server

Provision AI agents with their own email inboxes to send and receive messages programmatically. Developers integrate AgentMail to enable multi-agent communication and external email workflows.

ai.smithery/agentmail

Hosted URL

https://server.smithery.ai/agentmail

Transport

HTTP

Auth

No auth required

Smithery Agentmail repository at a glance

Live signal from GitHub, refreshed weekly.

Stars

4

Last commit

Mar 31, 2026

License

Language

TypeScript

What the Smithery Agentmail MCP server does

How models use it and what it is built for.

Provision AI agents with their own email inboxes to send and receive messages programmatically. Developers integrate AgentMail to enable multi-agent communication and external email workflows.

Connect to Smithery Agentmail

Hosted endpoint — paste into any MCP client.

https://server.smithery.ai/agentmail

Resources

Where to find authoritative docs and source for Smithery Agentmail.

Example prompts for Smithery Agentmail

Paste any of these into Agent Studio after connecting Smithery Agentmail.

  • Create a new email inbox for this agent and show me the inbox ID
  • Check for new emails in the agent's inbox and list unread messages
  • Send an email from the agent's inbox to user@example.com with subject line
  • What tools and resources does AgentMail expose for email operations

Documentation from project README

View on GitHub

Excerpted from the project's README — boilerplate sections (license, changelog, contributing) omitted for clarity.

Basic MCP Server

A minimal Model Context Protocol (MCP) server demonstrating tools, resources, and prompts.

Built with Smithery SDK

Prerequisites

Getting Started

  1. Install dependencies:

    npm install
    
  2. Start development server:

    npm run dev
    

Try the hello tool, history://hello-world resource, or greet prompt.

Development

Your code is organized as:

  • src/index.ts - MCP server with tools, resources, and prompts
  • smithery.yaml - Runtime specification

Edit src/index.ts to add your own tools, resources, and prompts.

Build

npm run build

Creates bundled server in .smithery/

Deploy

Ready to deploy? Push your code to GitHub and deploy to Smithery:

  1. Create a new repository at github.com/new

  2. Initialize git and push to GitHub:

    git add .
    git commit -m "Initial commit"
    git remote add origin https://github.com/YOUR_USERNAME/YOUR_REPO.git
    git push -u origin main
    
  3. Deploy your server to Smithery at smithery.ai/new

Continue reading on GitHub

Smithery Agentmail MCP server — FAQ

Common questions about connecting and running Smithery Agentmail.

  • What is AgentMail and how does it work?

    AgentMail is an email inbox API that gives AI agents their own email addresses and inboxes, similar to Gmail. Agents can send, receive, and manage emails programmatically through MCP tools and resources.

  • How do I authenticate with AgentMail?

    You need a Smithery API key from smithery.ai/account/api-keys. The MCP server uses this key to authenticate requests to the AgentMail service hosted at server.smithery.ai/agentmail.

  • Can I use AgentMail for multi-agent communication?

    Yes, AgentMail is designed to enable agents to communicate with each other and external systems via email. Each agent gets its own inbox, allowing asynchronous message passing between agents and users.

  • What are the available tools and resources in this MCP server?

    The basic MCP server includes example tools like `hello`, resources like `history://hello-world`, and prompts like `greet`. Refer to src/index.ts and the Smithery documentation to see the full AgentMail API surface.

  • How do I deploy AgentMail to production?

    Push your code to a GitHub repository, then deploy to Smithery at smithery.ai/new. The platform will build and host your MCP server, making it available at a stable endpoint.

Run Smithery Agentmail across 60+ AI models, side-by-side

Connect Smithery Agentmail to Claude, GPT, Gemini, DeepSeek and 60+ AI models in MCP Agent Studio. Compare answers side-by-side, save reusable agent presets, share runs — all in your browser, no install required.

Open Agent Studio

Related servers

More on MCP Playground