InboxAPI CLIofficial
A
licenseNot graded
qualityB
maintenanceProvides an AI agent with its own email address to send, receive, and manage emails via MCP. No email server setup required.
30 npm
13
MIT
Envoi MCP
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Envoi MCP send an email to hello@example.com about the project update"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
envoi-mcp
Give any AI agent a real email address. MCP server for Envoi.work.
Quick Start
npx envoi-mcpNo install required. Just add it to your AI client's MCP configuration.
Related MCP server: Email MCP Server
Setup
1. Get an API Key
Register your agent at envoi.work to get an API key and an @envoi.work email address.
2. Configure Your AI Client
Claude Code
claude mcp add envoi-mcp -e ENVOI_API_KEY=your-key-here -- npx envoi-mcpClaude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"envoi": {
"command": "npx",
"args": ["envoi-mcp"],
"env": {
"ENVOI_API_KEY": "your-key-here"
}
}
}
}Cursor
Add to .cursor/mcp.json:
{
"mcpServers": {
"envoi": {
"command": "npx",
"args": ["envoi-mcp"],
"env": {
"ENVOI_API_KEY": "your-key-here"
}
}
}
}Windsurf
Add to ~/.windsurf/mcp.json:
{
"mcpServers": {
"envoi": {
"command": "npx",
"args": ["envoi-mcp"],
"env": {
"ENVOI_API_KEY": "your-key-here"
}
}
}
}Tools
register_agent
Register a new AI agent on Envoi and get a real email address.
Input: { name, email, skills[], bio? }
Output: { api_key, email_address, profile_url, handle }send_email
Send an email from your agent's @envoi.work address.
Input: { to, subject, body }
Output: { success, message_id }check_inbox
List recent emails in the agent's inbox.
Input: { limit? }
Output: [{ id, from, subject, preview, date, read }]read_email
Read the full content of a specific email.
Input: { email_id }
Output: { from, to, subject, body, date, thread_id }reply_to_email
Reply to an email, maintaining the conversation thread.
Input: { email_id, body }
Output: { success, message_id }Environment Variables
Variable | Required | Description |
| Yes* | Your Envoi API key (*not required for |
| No | API base URL (default: |
Development
git clone https://github.com/yourusername/envoi-mcp.git
cd envoi-mcp
npm install
npm run buildTest locally:
ENVOI_API_KEY=your-key node dist/index.jsLicense
MIT
Available Tools
5 toolscheck_inboxC
List recent emails in the agent's inbox
Inputs: limit.
read_emailC
Read the full content of a specific email
Inputs: email_id (required).
register_agentB
Register a new AI agent on Envoi.work and get a real email address (@envoi.work)
Inputs: name (required), email (required), skills (required), bio.
reply_to_emailB
Reply to an email, maintaining the conversation thread
Inputs: email_id (required), body (required).
send_emailC
Send an email from your agent's @envoi.work address
Inputs: to (required), subject (required), body (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
A3.5/5.0
Scored across 5 tools
Disambiguation5/5
Each tool has a clearly distinct purpose with no overlap: check_inbox lists emails, read_email reads a specific email, register_agent sets up the agent, reply_to_email replies within a thread, and send_email sends new emails. The descriptions make it easy to distinguish between them, preventing misselection.
Naming Consistency5/5
All tools follow a consistent verb_noun pattern with snake_case (e.g., check_inbox, read_email, register_agent). The naming is predictable and readable throughout, with no deviations or mixed conventions.
Tool Count5/5
With 5 tools, the server is well-scoped for email management on Envoi.work. Each tool earns its place by covering core email operations (inbox, reading, sending, replying) and agent setup, without being too thin or bloated.
Completeness4/5
The toolset provides strong coverage for basic email workflows: agent registration, inbox listing, reading, sending, and replying. A minor gap is the lack of tools for managing emails (e.g., delete_email or archive_email), but agents can still handle core tasks effectively.
Maintenance
ActivityInactive
ResponsivenessNo recent community issues
Related MCP Connectors
Email inboxes for AI agents: send, receive, reply, search, and manage threaded email over MCP.
Email infrastructure for AI agents — send, receive, search, and reply to email over MCP.
Real email inboxes for AI agents: register, receive, read and send mail over MCP. Free to receive.
Hosted email MCP for AI agents with inboxes, send/receive, memory, recovery, and credits.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceGive AI agents their own email inboxes. Create, send, receive, and manage email entirely via MCP tools.-
- AlicenseNot gradedqualityDmaintenanceConnects any IMAP/SMTP mailbox to AI agents via MCP, enabling email read, search, send, reply, and management through natural language.13 npmMIT
- AlicenseAqualityBmaintenanceEnables AI agents to send, receive, and reply to email through dedicated thread-aware mailboxes, with sandbox testing and compatibility across MCP clients.957 npmMIT
