mcpField
M
Mailjet Mcp Server

Mailjet Mcp Server

Local
github.com/mailgunCommunication14Updated 11w ago

About Mailjet Mcp Server

Mailjet MCP Server connects Mailjet APIs to compatible AI agents through a standard tool interface. It is for teams working with contacts, campaigns, segments, statistics, and workflows.

Key features

  1. 01Access contacts and lists
  2. 02Manage campaigns and segments
  3. 03Retrieve sending statistics
  4. 04Use workflow APIs

Use cases

  1. 01Find the contact list with the most subscribers
  2. 02Summarize and chart recent email delivery statistics

MCP support

It exposes Mailjet API capabilities as tools for compatible MCP clients.

Configuration

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

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Mailjet MCP Server

MCP

Overview

This project provides a Model Context Protocol (MCP) server for the Mailjet API, enabling compatible AI agents (e.g. Claude Desktop) to interact with Mailjet's contact, campaign, segmentation, statistics, workflow (and more) APIs through a standardized tool interface.

Quick Start

Execution through NPX

The project is available on NPM and can be executed through NPX.

In order to start the server locally, simply run the following command:

MAILJET_API_KEY="YOUR_api_key:YOUR_secret_key" npx mailjet-mcp-server

Most of the time, you can choose to take advantage your AI desktop app and link Mailjet MCP directly to it. In this case please add the following MCP config:

"mcpServers": {
   "mailjet": {
      "command": "npx",
      "args": [
        "-y",
        "@mailjet/mailjet-mcp-server"
      ],
      "env": {
        "MAILJET_API_KEY": "YOUR_api_key:YOUR_secret_key"
      }
   }
}
Manual Installation
  1. Clone the repository:

    git clone https://github.com/mailgun/mailjet-mcp-server.git
    cd mailjet-mcp-server
    
  2. Install dependencies and build:

    pnpm install
    
  3. Configure Claude Desktop:

    Create or modify the config file:

    • MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
    • Windows: %APPDATA%/Claude/claude_desktop_config.json

Then start the MCP server:

node src/mailjet-mcp.js

Add the following configuration:

{
    "mcpServers": {
        "mailjet": {
            "command": "node",
            "args": ["CHANGE/THIS/PATH/TO/mailjet-mcp-server/src/mailjet-mcp.js"],
            "env": {
                "MAILJET_API_KEY": "YOUR_api_key:YOUR_secret_key"
            }
        }
    }
}
Supported environment variables

The following environment variables are currently supported by the server:

MAILJET_API_KEY="your_api_key:your_secret_key" # REQUIRED, used for authenticating your account
MAILJET_API_REGION="eu" # OPTIONAL, used to change to the EU servers, if desired

Testing

Run the local test suite with:

NODE_ENV=test pnpm test
Sample Prompts with Claude
Find contacts information
Which of my contacts lists has the most subscribers?
Fetch and Visualize Sending Statistics
Would you be able to make a chart with email delivery statistics for the past week?

Debugging

The MCP server communicates over stdio, please refer to Debugging section of the Model Context Protocol.

Publishing

This package is published on the Mailjet NPM registry. The Mailjet team is responsible for publishing new package updates. Feel free to create an issue if you noticed any divergence between the Github version and the NPM package available.

License

This project is licensed under the Apache License 2.0. See LICENSE for details.

Contributing

We welcome contributions! Please feel free to submit a Pull Request.

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.