Cloud Foundry MCP server for AI agents

The Cloud Foundry MCP Server provides an LLM interface that allows you to interact with your Cloud Foundry foundation using the Model Context Protocol (MCP). This server leverages the Spring AI MCP project to enable natural language interactions with your Cloud Foundry environment.

Installation

Building from Source

To build the server from source, run the following command in the project directory:

./mvnw clean package

This will create a JAR file in the target directory named cloud-foundry-mcp-0.0.1-SNAPSHOT.jar.

Configuration

Environment Setup

The MCP server requires several environment variables to connect to your Cloud Foundry foundation:

CF_APIHOST: Your Cloud Foundry API endpoint (e.g., api.sys.mycf.com)
CF_USERNAME: Your Cloud Foundry username
CF_PASSWORD: Your Cloud Foundry password
CF_ORG: Your organization name
CF_SPACE: Your space name

MCP Client Configuration

You need to configure your MCP client to connect to the server. Below is an example configuration for the claude_desktop_config.json file:

{
  "mcpServers": {
    "cloud-foundry": {
      "command": "java",
      "args": [
        "-Dspring.ai.mcp.server.transport=stdio", 
        "-Dlogging.file.name=cloud-foundry-mcp.log", 
        "-jar",
        "/path/to/cloud-foundry-mcp/target/cloud-foundry-mcp-0.0.1-SNAPSHOT.jar",
        "--server.port=8040"
      ],
      "env": {
        "CF_APIHOST": "[Your CF API Endpoint e.g. api.sys.mycf.com]",
        "CF_USERNAME": "[Your CF User]",
        "CF_PASSWORD": "[Your CF Password]",
        "CF_ORG": "[Your Org]",
        "CF_SPACE": "[Your Space]"
      }
    }
  }
}

Make sure to replace the placeholders in the env section with your actual Cloud Foundry credentials and the path to the JAR file in the args section with the actual path on your system.

Usage

After configuration, you can start using the MCP Server through your MCP-compatible LLM client. The server enables you to use natural language to:

Query information about your Cloud Foundry environment
Manage applications, services, and routes
Retrieve logs and status information
Perform other operations typically available through the CF CLI

Simply direct your queries to the "cloud-foundry" MCP server in your LLM interface, and the server will interpret your natural language requests into Cloud Foundry operations.

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "cloud-foundry" '{"command":"java","args":["-Dspring.ai.mcp.server.transport=stdio","-Dlogging.file.name=cloud-foundry-mcp.log","-jar","/path/to/cloud-foundry-mcp/target/cloud-foundry-mcp-0.0.1-SNAPSHOT.jar","--server.port=8040"],"env":{"CF_APIHOST":"[Your CF API Endpoint e.g. api.sys.mycf.com]","CF_USERNAME":"[Your CF User]","CF_PASSWORD":"[Your CF Password]","CF_ORG":"[Your Org]","CF_SPACE":"[Your Space]"}}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cloud-foundry": {
            "command": "java",
            "args": [
                "-Dspring.ai.mcp.server.transport=stdio",
                "-Dlogging.file.name=cloud-foundry-mcp.log",
                "-jar",
                "/path/to/cloud-foundry-mcp/target/cloud-foundry-mcp-0.0.1-SNAPSHOT.jar",
                "--server.port=8040"
            ],
            "env": {
                "CF_APIHOST": "[Your CF API Endpoint e.g. api.sys.mycf.com]",
                "CF_USERNAME": "[Your CF User]",
                "CF_PASSWORD": "[Your CF Password]",
                "CF_ORG": "[Your Org]",
                "CF_SPACE": "[Your Space]"
            }
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "cloud-foundry": {
            "command": "java",
            "args": [
                "-Dspring.ai.mcp.server.transport=stdio",
                "-Dlogging.file.name=cloud-foundry-mcp.log",
                "-jar",
                "/path/to/cloud-foundry-mcp/target/cloud-foundry-mcp-0.0.1-SNAPSHOT.jar",
                "--server.port=8040"
            ],
            "env": {
                "CF_APIHOST": "[Your CF API Endpoint e.g. api.sys.mycf.com]",
                "CF_USERNAME": "[Your CF User]",
                "CF_PASSWORD": "[Your CF Password]",
                "CF_ORG": "[Your Org]",
                "CF_SPACE": "[Your Space]"
            }
        }
    }
}

3. Restart Claude Desktop for the changes to take effect