Amplify Fusion Artificial Intelligence

How to set up an MCP server for your APIs with Amplify Fusion

| Jeroen Delbarre |
Step-by-Step Guide on how to setup an MCP server on top of your APIs

In a previous article, I shared how MCP (model context protocol) is essential to helping LLMs perform actions and enable agentic AI — and described the value it can bring to your business. So, how do you implement a real-life use case using MCP and integrate that with a chatbot such as Claude?

In this article, we’ll dive into setting up Amplify Fusion so it can be used to create an MCP server on top of your existing APIs. This allows you to leverage API functionality through a chatbot. And because Fusion can be used to build APIs on top of your legacy systems, you can basically integrate any of your company’s capabilities into a chatbot.

Read on for a step-by-step guide that shows you how to configure Fusion for MCP.

Example MCP use case for a weather API

A user will use Claude Desktop to ask what the weather is like in a certain location. Claude Desktop is integrated through MCP with the MCP server that is running on Amplify Fusion.

The MCP server will implement the Weather API. The diagram below gives a simplified visual representation of the setup.

 

 

Walkthrough of an MCP server setup with Amplify Fusion

An MCP server is created in Amplify Fusion to expose the weather API as a tool. The MCP server can be consumed using HTTP streaming.

 

"MCP Server configuration interface showing weather API setup. The screen displays a configuration panel with General, Security, and Transport Security tabs. The right side shows the MCP HTTP Streaming Transport API (version 1.0.0, OAS 3.0) with JSON-RPC 2.0 specification support. The frontend path is set to '/weather' with POST method enabled for the MCP endpoint.

 

The MCP server in Fusion is protected with an API key and the API key will be configured in Claude Desktop to call the MCP server.

Before the MCP server can be used, it needs to be activated and during activation a URL is shown on which the MCP server can be called.

 

Shared Data Plane connection status interface showing 'Public SaaS Data Plane' with 'Connected' status in green. An 'Axway Managed' button appears in the top right, with a dropdown displaying the sandbox URL: https://aitrailblazers-design.sandbox.ampint.axwaytest.net:4443/weather

 

We can now go to Claude Desktop and edit the config to add the MCP server:

 

Claude Desktop app Settings page showing MCP (Model Context Protocol) configuration. The interface displays a dark-themed settings modal with 'General' and 'Developer' tabs on the left. The main panel explains that 'Claude can receive information like prompts and attachments from specialized servers using Model Context Protocol' and describes MCP as 'a protocol that enables secure connections between clients, such as the Claude Desktop app, and local services.' Two buttons are available at the bottom: 'Edit Config' and an orange 'Get Started' button.

 

We add the MCP server configuration:

 

"weather": {

      "command": "npx",

      "args": [

        "mcp-remote",

        "https://<fusionhost>/weather/mcp?X-API-Key=<APIKey>"

      ]

    }

 

And the configuration will look like this:

 

Code editor showing claude_desktop_config.json file with MCP server configuration. The JSON structure defines a 'weather' server using the 'npx' command with arguments including 'mcp-remote' and a URL endpoint 'https://aitrailblazers.axway.com:4443/weather/mcp' with an API key parameter. Line numbers are visible on the left, and the URL is highlighted in blue as a hyperlink.

 

After restarting Claude Desktop, you will see the weather tool:

 

Claude AI interface showing a personalized greeting 'Good evening, Jeroen' with a coral-colored asterisk icon. The interface displays a dark theme with a text input field asking 'How can I help you today?' Below are input options and a dropdown menu showing search results for 'weather' with a notification badge indicating 1 result. The top of the screen shows 'Free plan • Upgrade' and the bottom right indicates 'Claude 3.7 Sonnet' is being used. Additional buttons for 'Life stuff' and 'Claude's choice' appear as conversation starters.

 

Now, if you ask a question about the weather, Claude will suggest that you use the weather lookup tool:

 

Screenshot of Claude AI providing weather information for New York. The image shows a conversation where a user with initials 'JD' asks 'What is the weather like in New York?' Claude responds by explaining it will check using geographical coordinates, followed by a dropdown labeled 'weather-lookup.' The response states that New York is currently experiencing 22.8°C (73°F) with few clouds, a light breeze of 4.6 m/s from the west, 45% humidity, and 10 km visibility. It mentions it's a pleasant day with 20% cloud cover, sunrise at 6:07 AM, and sunset at 7:58 PM. Claude concludes by asking if there's anything specific about New York weather the user would like to know more about.

 

The response that Claude Desktop has constructed is based on the information returned by the Weather API, which is running in Amplify Fusion.

This use case shows how to retrieve information from an API, but the same principle can be applied to call an API to execute an action, such as: update the status of my order or send my invoice for processing.

Now that you’ve seen how you can use Amplify Fusion to create an MCP server that can be used by an MCP host, such as Claude Desktop, what more could you do with Fusion?

Discover how Axway’s Amplify Fusion helps you rapidly design, test, and deploy integration processes.

Click Here