mcpField
S
sendsoon

sendsoon

Local
sendsoonai.comCommunication6Updated 2w ago

About sendsoon

SendSoon AI MCP provides email sending, public IP lookups, and local document-to-Markdown conversion for AI clients. It is intended for users who want these SendSoon services available as tools through natural-language requests.

Key features

  1. 01Send single emails
  2. 02Look up public IP information
  3. 03Convert local documents to Markdown
  4. 04Configure with an optional API key

Use cases

  1. 01Send a meeting reminder email
  2. 02Check an IP address location and ISP
  3. 03Convert a PDF report to Markdown
  4. 04Summarize a converted document

MCP support

Exposes SendSoon email, IP lookup, and document conversion tools to MCP clients such as Codex, Claude Desktop, and WorkBuddy. The README documents local setup and testing with MCP Inspector.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"sendsoon": {
"command": "npx",
"args": [
"-y",
"@sendsoon/mcp"
],
"env": {
"SENDSOON_API_KEY": "<SENDSOON_API_KEY>"
}
}
}
}
Run commandnpx -y @sendsoon/mcp
Environment variables to set
SENDSOON_API_KEYSecretSendSoon API Key (ssk_live_...). Leave empty for the anonymous trial of three sends per public IP per day.

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@sendsoon/mcp0.3.8
pypisendsoon-mcp0.3.8

Tools

3

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
tostringYesRecipient email address
bodystringYesEmail body (plain text or HTML; max 512,000 UTF-8 bytes)
subjectstringYesEmail subject line
content_typeenumNoMIME content type for body (default: text/plain)text/plain | text/html
idempotency_keystringNoOptional stable key that prevents duplicate delivery when callers retry

Details

From the project README

SendSoon AI MCP

English | 简体中文 | 日本語

SendSoon MCP is a Model Context Protocol (MCP) server that lets Codex, Claude, and WorkBuddy use SendSoon capabilities: send email, look up public IPs, and convert local documents to Markdown.

Configure it once, then describe tasks in natural language. You usually do not need to mention SendSoon in every prompt.

What you can do

ToolPurposeExample
send_emailSend a single email“Send me a test email”
ip_lookupLook up public IP information“Look up the location of 8.8.8.8”
markitdown_convertConvert a local document to Markdown“Convert this PDF to Markdown”

Everyday examples

Send an email to [email protected] with the subject “Meeting reminder” and the body “The meeting starts at 3 PM today.”
Look up the location and ISP for 8.8.8.8.
Convert /path/to/report.pdf to Markdown and summarize the key points.

If the agent does not select a tool automatically, say:

Use the sendsoon MCP to complete this task.

Install in your AI client

The instructions below cover Codex, Claude Desktop, and WorkBuddy.

Codex

Config file: user-level ~/.codex/config.toml (macOS / Linux) or %USERPROFILE%\.codex\config.toml (Windows).

[mcp_servers.sendsoon]
command = "npx"
args = ["-y", "@sendsoon/mcp"]

[mcp_servers.sendsoon.env]
SENDSOON_API_KEY = ""

Verify: Save the file, restart Codex, and run /mcp in a chat. You should see sendsoon connected. In the desktop app, also check Settings > MCP servers.

First use: Start a new conversation and ask for a simple task (e.g. “Look up 8.8.8.8”). Approve the tool if Codex asks for permission.

Claude Desktop

Config file:

OSPath
macOS~/Library/Application Support/Claude/claude_desktop_config.json
Windows%APPDATA%\Claude\claude_desktop_config.json

You can also open Settings > Developer > Edit Config inside Claude Desktop.

{
  "mcpServers": {
    "sendsoon": {
      "command": "npx",
      "args": ["-y", "@sendsoon/mcp"],
      "env": {
        "SENDSOON_API_KEY": ""
      }
    }
  }
}

Verify: Save the file, fully quit Claude Desktop (including the system tray), then relaunch. Start a new chat and confirm sendsoon tools appear in the tools menu or settings.

First use: Claude may ask to approve tool access on the first invocation; allow it to continue.

WorkBuddy

WorkBuddy can add SendSoon by pasting the connector JSON directly in MCP Server Management.

Config file: %USERPROFILE%\.workbuddy-ai\mcp.json (Windows) or ~/.workbuddy-ai/mcp.json (macOS / Linux).

  1. Open WorkBuddy and go to MCP Server Management.
  2. Click Add MCP.
  3. Paste the JSON below into the editor. Fill in SENDSOON_API_KEY if you have a Key; leave it empty for the anonymous trial.
  4. Click Save.
{
  "mcpServers": {
    "sendsoon": {
      "command": "npx",
      "args": [
        "-y",
        "@sendsoon/mcp"
      ],
      "env": {
        "SENDSOON_API_KEY": ""
      }
    }
  }
}

WorkBuddy MCP Server Management with the SendSoon connector JSON

The screenshot shows the WorkBuddy connector editor: the configuration file path is at the top, and the sendsoon JSON is pasted into the editor. After saving, return to the MCP list and confirm sendsoon is connected.

Verify: Start a new conversation and ask for a simple task (e.g. “Look up 8.8.8.8”). Approve the tool if WorkBuddy asks for permission.

Prepare the configuration

Optional environment variable:

SettingRequiredWhat to enter
SENDSOON_API_KEYNoLeave empty for an unregistered trial. One public IP can send up to three free test emails per day. Enter your generated Key for continued use

Never commit a real Key to Git or share it with anyone.

Get an API Key
  1. Sign up or sign in on the SendSoon registration page.
  2. Open Profile and generate a Key in the API Key section.
  3. Copy the one-time ssk_live_... Key immediately and enter it as SENDSOON_API_KEY in your MCP configuration.
  4. Save the configuration and restart your MCP client. Requests with a valid Key do not use the anonymous IP daily quota.

If the anonymous quota is exhausted, send_email will tell you to register and configure a Key. An invalid or revoked Key is rejected and does not fall back to the anonymous quota.

Try it in Google Colab

Skip local setup and try ip_lookup, markitdown_convert, and send_email in the browser.

Open in Colab

The notebook calls the same SendSoon HTTP APIs used by these MCP tools.


Visual local testing (MCP Inspector)

To see all three tools in a browser and click through them manually before installing into an AI client, use the MCP Inspector.

Requires Node.js 20+. Run the command below in a terminal; Inspector opens a web UI automatically:

npx @modelcontextprotocol/inspector npx -y @sendsoon/mcp
How to test
  1. Wait for MCP Inspector Web is up and running in the terminal. If the browser does not open, paste the http://127.0.0.1:6274?... URL from the terminal.
  2. Confirm the page header shows Connected.
  3. Open the Tools tab in the top-right area of the page.
  4. Select a tool from the list on the left, fill in the parameters, and click Execute Tool.
  5. Read the response in the Results panel on the right. On failure, inspect error.code and error.message.

License

See LICENSE.

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.