Сonnect and use SendPulse’s MCP server for AI integrations

SendPulse’s MCP server is a tool that helps you manage your account through a chat with an AI assistant. It uses SendPulse API methods to get information and perform actions, such as request statistics, run message campaigns, or update user data.

You can connect this MCP server to OpenAI, Claude, Cursor IDE, and more. Choose an environment, and the server will connect it with your SendPulse account.

In this article, we will explain how to connect SendPulse’s MCP server through OpenAI and Cursor IDE clients and how you can use its features.

Basics

MCP server acts as middleware between your AI assistant and your SendPulse account. It processes requests through the SendPulse API and sends results back to chat, so you can manage everything without leaving the conversation.

Key terms to learn before setup:

• Client is the app where you chat with your AI assistant, such as ChatGPT or Cursor IDE.
• MCP server is the middleware between the client and your SendPulse account. It shows available actions and executes them through the API.
• Tools are specific actions you can perform in your account.

Once connected, the MCP server operates as follows:

1. You ask your AI assistant something in chat.
2. It forwards your request to the MCP server.
3. The MCP server calls the API to get data or perform an action.
4. The AI assistant sends the result back to your chat.

All requests are billed according to your client’s API pricing policy.

Connect the MCP server

Copy the MCP server link

In your SendPulse account, go to Account settings > API. In MCP, copy the link. You will need to paste this link into your MCP client to authorize and access the supported API methods.

Connect the MCP server in your client

Connect through OpenAI

In the OpenAI API platform, go to Dashboard > Chats and click Create. In Tools, click + Add and select MCP Server.

In the modal window, click + Create and fill in the fields:

Click Connect. In the next window, go over the access request and click Add.

Connect through Cursor IDE

In Cursor, go to Cursor Settings > MCP and click Add Custom MCP.

Click Connect. In the next window, go over the access request and click Add.

Copy the code below and paste it into the configuration file that opens:

{
  "mcpServers": {
    "sendpulse_mcp_service": {
      "url": "https://mcp.sendpulse.com/mcp"
    }
  }
}

Save the changes and return to the MCP settings. Next to the sendpulse_mcp_service server, click Connect.

You will be redirected to the SendPulse API authorization page. Enter your account credentials and confirm the access request from your AI assistant.

Use the MCP server

Once you’ve connected the MCP server, you can send messages and perform other actions in your SendPulse account using the available tools.

View tools

To view all available commands and manage access in your client, open the Tools section.

SendPulse’s MCP server is currently integrated with chatbot builder, CRM, Email service and SMTP. Read more: List of MCP commands.

To view a tool description and required request parameters, click the arrow next to it.

Chat with your AI assistant

In the chat, you can type in your requests in free form. The AI assistant will then name the tool it plans to run. If it looks correct, click Approve to let it run the action in your account. If you have several bots or subscribers with the similar name, AI assistant will ask which one you need.

Here's how request results are returned to your chat:

• If successful, you will receive account information or action result data.
• If an error occurs, check your client logs and authorization status.

Last Updated: 29.09.2025