- Explore MCP Servers
- mcp-server
Integration App MCP Server
What is Integration App MCP Server
The Integration App MCP Server is an implementation of the Model Context Protocol (MCP) that serves as a bridge to connect clients with various tools available via Integration App. It exposes tools through Server-Sent Events (SSE), allowing real-time updates and interactions for connected clients.
Use cases
This MCP server can be utilized by various client applications where real-time data streaming and interaction with tools are required. It is particularly useful for applications that integrate AI functionalities, chat agents, or any interactive utilities needing dynamic resource retrieval from active connections.
How to use
To use the MCP server, clone the repository, install dependencies, and build the project. Start the server locally or deploy it to a cloud service. Connect clients using the specified URL format that includes a valid Integration App Token for authentication. Additionally, configure client-specific settings for tools like Cursor or Claude to enable seamless integration.
Key features
Key features of the MCP server include support for SSE transport for continuous real-time updates, ease of deployment on various cloud platforms, and an integration mechanism with existing tools. The server dynamically fetches tools from active connections based on the provided token, enhancing interaction capabilities.
Where to use
The MCP server is ideally used in environments requiring dynamic tool access and integration, such as AI applications, chatbots, and any interactive web or desktop applications that facilitate real-time data communication and user engagement.
Overview
What is Integration App MCP Server
The Integration App MCP Server is an implementation of the Model Context Protocol (MCP) that serves as a bridge to connect clients with various tools available via Integration App. It exposes tools through Server-Sent Events (SSE), allowing real-time updates and interactions for connected clients.
Use cases
This MCP server can be utilized by various client applications where real-time data streaming and interaction with tools are required. It is particularly useful for applications that integrate AI functionalities, chat agents, or any interactive utilities needing dynamic resource retrieval from active connections.
How to use
To use the MCP server, clone the repository, install dependencies, and build the project. Start the server locally or deploy it to a cloud service. Connect clients using the specified URL format that includes a valid Integration App Token for authentication. Additionally, configure client-specific settings for tools like Cursor or Claude to enable seamless integration.
Key features
Key features of the MCP server include support for SSE transport for continuous real-time updates, ease of deployment on various cloud platforms, and an integration mechanism with existing tools. The server dynamically fetches tools from active connections based on the provided token, enhancing interaction capabilities.
Where to use
The MCP server is ideally used in environments requiring dynamic tool access and integration, such as AI applications, chatbots, and any interactive web or desktop applications that facilitate real-time data communication and user engagement.
Content
Integration App MCP Server
This is an implementation of the MCP (Model Context Protocol) server that exposes tools powered by Integration App. It allows clients to connect and access tools from active connections, using the MCP SSE transport.
To implement your own MCP client, see our example AI Chat Agent:
Prerequisites
- Node.js (v14 or higher)
- npm or yarn
- An Integration App account
Installation
-
Clone the repository:
git clone https://github.com/integration-app/mcp-server cd mcp-server
-
Install dependencies:
npm install
-
Build the project:
npm run build
Configuration
Local Development
To run the server locally, start it with:
npm start
The server will run on http://localhost:3000
.
Deployment
To deploy the server to a production environment (e.g., Heroku), follow these steps:
-
Ensure your environment variables are set:
PORT
: The port on which the server will run (default: 3000)NODE_ENV
: Set toproduction
for production environments
-
Deploy your application using your preferred hosting service (e.g., Heroku, AWS, etc.).
-
Once deployed, your server will be accessible at a URL like:
https://your-app-name.herokuapp.com/
Connection URL
To connect to the MCP server, use the following URL format:
https://your-app-name.herokuapp.com/sse?token=YOUR_TOKEN
Or, if the server is running locally:
http://localhost:3000/sse?token=YOUR_TOKEN
Replace YOUR_TOKEN with a valid Integration App Token. You can get a Test Access Token from the Integration App Console by navigating to Settings > Testing > Test Access Token.
Cursor Configuration
To use this server with Cursor, update the ~/.cursor/mcp.json
file:
{
"mcpServers": {
"integration-app": {
"url": "https://your-app-name.herokuapp.com/sse?token=YOUR_TOKEN"
}
}
}
Restart Cursor for the changes to take effect.
Claude Desktop Configuration
Anthropic only allows SSE MCP tranports to Claude with MAX plan or higher. To use this server with Claude, update the config file (Settings > Developer > Edit Config):
{
"mcpServers": {
"integration-app": {
"url": "https://your-app-name.herokuapp.com/sse?token=YOUR_TOKEN"
}
}
}
MCP Information
- The server fetches tools from all active connections associated with the provided token.
- The server supports SSE (Server-Sent Events) transports.
Troubleshooting
- Ensure your Integration App token is valid (you’re using a Test Access Token or generated a token according to these instructions)
- Check server logs for any errors or issues during startup or connection attempts.
- Verify that your deployment environment has the correct environment variables set.