Back to MCP Catalog

Integration App Tools MCP Server

Developer ToolsJavaScript
Connect AI models to your Integration App workspace tools

Integration App MCP Server provides a bridge between AI models and your Integration App workspace. It exposes actions defined in your Integration App workspace as tools that can be used by AI models through the Model Context Protocol (MCP). This allows AI assistants to interact with your business systems and perform operations through the integrations you've configured.

Overview

Integration App MCP Server implements the Model Context Protocol (MCP) to expose tools powered by Integration App. This server allows AI models to access and use actions defined in your Integration App workspace, enabling AI assistants to interact with your business systems and perform operations through your configured integrations.

Prerequisites

Before setting up the Integration App MCP Server, you need:

  1. Node.js installed on your system
  2. An Integration App workspace with configured actions
  3. Integration App authentication credentials:

Installation

To install and run the Integration App MCP Server, you need to configure your AI assistant's client with the appropriate settings.

Add the following configuration to your AI assistant's client configuration file (e.g., claude_desktop_config.json):

{
  "mcpServers": {
    "integration-app-tools": {
      "command": "npx",
      "args": ["-y", "@integration-app/mcp-server"],
      "env": {
         "INTEGRATION_APP_TOKEN": "<your-integration-app-token>",
         "INTEGRATION_KEY": "<your-integration-key>"
      }
    }
  }
}

Replace <your-integration-app-token> with your actual Integration App token and <your-integration-key> with the key of the integration you want to expose tools for.

Configuration

The server requires two environment variables:

  • INTEGRATION_APP_TOKEN: Your token for accessing the Integration App API
  • INTEGRATION_KEY: The key of the integration you want to use tools for

Note that this server exposes tools from one integration at a time. If you need to expose tools from multiple integrations, you can either:

  1. Create multiple server instances with different configurations
  2. Modify the code to iterate over multiple integrations

Testing

After setting up the server, you can test if it's working correctly by asking your AI assistant what tools are available. The assistant should list all the tools that are configured in your Integration App workspace for the specified integration.

Managing Tools

The tools exposed by this server are based on Actions defined in your Integration App workspace. To effectively manage these tools:

  1. Log in to your Integration App console
  2. Navigate to the integration you want to configure
  3. Define or modify actions as needed
  4. Ensure the actions have appropriate input schemas for the AI to understand how to use them

For more detailed information on managing tools, refer to the Using Tools guide in the Integration App documentation.

Related MCPs

Apple Shortcuts
Developer ToolsJavaScript

Control Apple Shortcuts automations from AI assistants

Clojars Dependency Lookup
Developer ToolsJavaScript

Fetch dependency information from Clojars, the Clojure community's artifact repository

Simple Timeserver
Developer ToolsPython

Provides Claude with current time and timezone information

About Model Context Protocol

Model Context Protocol (MCP) allows AI models to access external tools and services, extending their capabilities beyond their training data.

Generate Cursor Documentation

Save time on coding by generating custom documentation and prompts for Cursor IDE.