Pulumi MCP server

The MCP Server is a tool that allows AI assistants and clients to interact with Pulumi infrastructure as code through the Model Context Protocol (MCP). It provides a standardized way for AI clients to manage cloud infrastructure using natural language instructions via supported MCP clients like Claude Desktop, VSCode, and Cline.

Installation

Prerequisites

• Docker installed on your system
• A Pulumi access token

Setting Up the MCP Server

To run the MCP server, you'll need to use Docker with the following configuration:

docker run -i --rm --name pulumi-mcp-server -e PULUMI_ACCESS_TOKEN=${YOUR_TOKEN} dogukanakkaya/pulumi-mcp-server

Replace ${YOUR_TOKEN} with your actual Pulumi access token.

Client Configuration

Configuring in VS Code

To add the Pulumi MCP server to your VS Code setup:

1. Open VS Code settings
2. Navigate to the MCP servers configuration section
3. Add the following configuration:

{
  "pulumi-mcp-server": {
    "command": "docker",
    "args": [
      "run",
      "-i",
      "--rm",
      "--name",
      "pulumi-mcp-server",
      "-e",
      "PULUMI_ACCESS_TOKEN",
      "dogukanakkaya/pulumi-mcp-server"
    ],
    "env": {
      "PULUMI_ACCESS_TOKEN": "your-pulumi-token-here"
    },
    "transportType": "stdio"
  }
}

Configuring in Cline

To add the Pulumi MCP server to Cline:

1. Navigate to the Cline configuration settings
2. Add a new MCP server with the same configuration as above
3. For detailed steps, refer to the Cline MCP Server configuration documentation

Usage

Once configured, you can interact with the Pulumi MCP server through your chosen MCP client. The server allows AI assistants to:

• Read and understand your Pulumi infrastructure code
• Help write and modify Pulumi programs
• Provide infrastructure as code assistance
• Answer questions about your cloud resources

For additional supported clients and detailed documentation, visit the Model Context Protocol website.

How to add this MCP server to 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 > MCP and click "Add new global MCP server".

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

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

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 explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.