Inbound Email MCP Server

Inbound Email MCP Server

Enables AI assistants to interact with the Inbound Email API to manage domains, endpoints, and email communications. Users can send or schedule emails, manage webhooks, and retrieve email threads through natural language commands.

Category
Visit Server

README

@inbound/mcp

MCP (Model Context Protocol) server for the Inbound Email API. Give your AI agent its own email address to send, receive, and manage emails.

Quick Start: Agent Mailbox

The primary use case is giving an AI agent its own email identity. Set the x-inbound-mailbox header to your agent's email address:

{
  "mcpServers": {
    "inbound": {
      "url": "http://localhost:5454/mcp",
      "headers": {
        "x-inbound-api-key": "your-api-key",
        "x-inbound-mailbox": "Support Agent <support@yourdomain.com>"
      }
    }
  }
}

The header supports both formats:

  • With display name: Support Agent <support@yourdomain.com>
  • Email only: support@yourdomain.com

Mailbox Tools

Tool Description
check_mailbox Check incoming emails for your mailbox (defaults to unread)
get_mailbox_threads Get conversation threads where your mailbox is a participant
send_from_mailbox Send emails - from is automatically set to your mailbox
reply_from_mailbox Reply to emails/threads - from is automatically set to your mailbox

Agent Workflow

  1. Check for new emails: check_mailbox returns unread emails with IDs
  2. Read email details: Use get_email with the email ID to read full content
  3. Reply to emails: reply_from_mailbox sends replies with your agent identity
  4. Send new emails: send_from_mailbox sends emails as your agent

When sending, the display name (e.g., "Support Agent") is included so recipients see a friendly sender name.

Installation

npm install @inbound/mcp
# or
pnpm add @inbound/mcp
# or
bun add @inbound/mcp

Configuration

Claude Desktop (STDIO)

Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):

{
  "mcpServers": {
    "inbound": {
      "command": "npx",
      "args": ["-y", "@inbound/mcp"],
      "env": {
        "INBOUND_API_KEY": "your-api-key",
        "INBOUND_MAILBOX": "Agent <agent@yourdomain.com>"
      }
    }
  }
}

Cursor / Other MCP Clients (HTTP)

Start the server:

npx @inbound/mcp start:http

Then configure your client:

{
  "mcpServers": {
    "inbound": {
      "url": "http://localhost:5454/mcp",
      "headers": {
        "x-inbound-api-key": "your-api-key",
        "x-inbound-mailbox": "Agent <agent@yourdomain.com>"
      }
    }
  }
}

Authentication

The MCP server authenticates using your Inbound API key:

  • Environment variable: INBOUND_API_KEY
  • HTTP header: x-inbound-api-key

Optional: Domain Restriction

To restrict all operations to a single domain:

  • Environment variable: INBOUND_DOMAIN
  • HTTP header: x-inbound-domain

All Available Tools

Mailbox (Agent Mode)

  • check_mailbox - Check incoming emails for your mailbox
  • get_mailbox_threads - Get conversation threads for your mailbox
  • send_from_mailbox - Send an email from your mailbox
  • reply_from_mailbox - Reply to an email from your mailbox

Emails

  • list_emails - List sent, received, and scheduled emails
  • get_email - Get detailed information about a specific email
  • send_email - Send or schedule an email
  • reply_email - Reply to an email or thread
  • retry_email - Retry delivery of a failed email

Threads

  • list_threads - List email conversations
  • get_thread - Get all messages in a thread

Domains

  • list_domains - List all domains in your account

Endpoints

  • list_endpoints - List webhook and email forwarding endpoints
  • create_endpoint - Create a webhook, email forward, or email group endpoint

Available Prompts

  • getting-started - Learn how to use Inbound Email API

Development

# Install dependencies
pnpm install

# Run in development mode
pnpm dev

# Build for production
pnpm build

License

Apache-2.0

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
E2B

E2B

Using MCP to run code via e2b.

Official
Featured