Sendmux MCP Server

Email inbox API for AI agents with MCP tools for Mailbox, Management, and Sending APIs.

Remote serverstreamable-httpPython

What is the Sendmux MCP MCP server?

If you already use Sendmux MCP, the sendmux mcp mcp server is the piece that lets your assistant work with it directly. Email inbox API for AI agents with MCP tools for Mailbox, Management, and Sending APIs.

What the server does

Use send-capable smx_mbx_* keys or owner-approved Sending-resource smx_agent_* tokens for Sending clients. Use smx_mbx_* keys or scoped smx_agent_* tokens for Mailbox clients. Use root smx_root_* keys for Management clients. Agent tokens remain limited by server-side scopes; pre-claim self-registered agent tokens do not include email.send.

Installation

Because this one is hosted, setup is mostly authentication — you point your client at the endpoint and approve access. Nothing runs on your machine, so there is no runtime to keep patched.

Available tools

The toolset is worth reading before you wire it up, because it tells you what the integration is really for:

  • CLI — sendmux mailbox:send-message --attach ./report.pdf or sendmux sending:send --attach ./report.pdf
  • TypeScript — use @sendmux/mailbox/node sendMailboxMessageWithFiles(...) or @sendmux/sending/node sendEmailWithFiles(...)
  • MCP — local stdio can use mailbox_upload_attachment with file_path; hosted and shell-capable agents can mint a presigned upload URL, PUT bytes to it
  • Ecosystem — Package
  • Homebrew — sendmux
  • PyPI — sendmux-core
  • crates.io — sendmux
  • Packagist — sendmux/core
  • RubyGems — sendmux-core
  • Path — Purpose

Worth knowing first

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • With 10 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Sendmux MCP.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Where it fits

Plenty of team communication servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Sendmux MCP's toolset — CLI, TypeScript, MCP and 7 more — is a fair guide to whether it matches your workflow. It is maintained by Sendmux; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Available tools

ToolWhat it does
CLIsendmux mailbox:send-message --attach ./report.pdf or sendmux sending:send --attach ./report.pdf.
TypeScriptuse @sendmux/mailbox/node sendMailboxMessageWithFiles(...) or @sendmux/sending/node sendEmailWithFiles(...).
MCPlocal stdio can use mailbox_upload_attachment with file_path; hosted and shell-capable agents can mint a presigned upload URL, PUT bytes to it without an API key, then send with the returned blob_id.
EcosystemPackage
Homebrewsendmux
PyPIsendmux-core
crates.iosendmux
Packagistsendmux/core
RubyGemssendmux-core
PathPurpose

How to install the Sendmux MCP MCP server

{
  "mcpServers": {
    "sendmux": {
      "command": "npx",
      "args": ["-y", "@sendmux/core"]
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Example prompts to try

  • Use Sendmux MCP to CLI.
  • Use Sendmux MCP to TypeScript.
  • Use Sendmux MCP to MCP.

Frequently asked questions

It connects Sendmux MCP to MCP-compatible AI assistants such as Claude and Cursor, exposing 10 tools (CLI, TypeScript, MCP, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Sendmux MCP directly.