Pulumi MCP Server

What does “Pulumi” MCP Server do?

The Pulumi MCP Server acts as a bridge between AI assistants and the Pulumi infrastructure-as-code platform. By exposing Pulumi operations through the Model Context Protocol (MCP), this server enables AI-powered development workflows, allowing clients (such as Claude Desktop, VSCode, and Cline) to interact with cloud infrastructure programmatically. Using this server, AI assistants can perform tasks like deploying resources, managing stacks, querying state, and automating routine infrastructure operations. This integration streamlines infrastructure management, reduces manual intervention, and empowers developers to control cloud environments directly from their preferred AI-enhanced tools.

List of Prompts

No information about prompt templates was found in the repository.

Ready to grow your business?

Start your free trial today and see results within days.

Request demo Log in

List of Resources

No specific MCP “resources” are listed or exposed by the Pulumi MCP Server in the repository.

List of Tools

No explicit tools are enumerated in the documentation or visible in the repository’s surface files. The main functionality appears centered around running Pulumi operations via Docker.

Join our newsletter

Get latest tips, trends, and deals for free.

Email address

Subscribe

Use Cases of this MCP Server

• Cloud Infrastructure Deployment: Developers can deploy and manage cloud infrastructure directly from their AI-enhanced development environments, reducing context switching and manual command-line work.
• Automated Infrastructure Updates: AI assistants can automate routine updates to cloud resources, ensuring consistency and reducing human error.
• Stack Management: Easily create, update, or destroy Pulumi stacks as part of automated workflows, enhancing DevOps productivity.
• Resource Querying: Query the state and output of cloud resources via AI, enabling rapid troubleshooting and infrastructure insight.
• Integration with IDEs and Chatbots: Use within tools like VSCode, Claude Desktop, or Cline to trigger infrastructure actions as part of conversational or code-centric workflows.

How to set it up

Windsurf

No setup instructions for Windsurf are provided in the repository.

Claude

1. Ensure Docker is installed on your system.
2. Obtain your PULUMI_ACCESS_TOKEN.
3. Locate the MCP server configuration section in Claude Desktop.
4. Add the following JSON to your mcpServers 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_TOKEN}"
       },
       "transportType": "stdio"
     }
   }
   

5. Save your configuration and restart Claude Desktop as needed.

Securing API Keys:
Store your Pulumi access token in an environment variable. In your configuration, use:

"env": {
  "PULUMI_ACCESS_TOKEN": "${YOUR_TOKEN}"
}

Cursor

No setup instructions for Cursor are provided in the repository.

Cline

1. Ensure Docker is installed.
2. Acquire your PULUMI_ACCESS_TOKEN.
3. Open the MCP server config for Cline.
4. Insert:

   {
     "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_TOKEN}"
       },
       "transportType": "stdio"
     }
   }
   

5. Save and restart Cline to load the new server.

Securing API Keys:
See the above env usage example.

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "pulumi-mcp-server": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent can use this MCP as a tool with access to all its functions and capabilities. Remember to change “pulumi-mcp-server” to the actual name of your MCP server and replace the URL with your own MCP server URL.

Overview

ROOTS support: Not documented
Sampling support: Not documented

Based on the information found, the Pulumi MCP Server repository is functional and integrates Pulumi with MCP clients, but lacks documentation on prompts, resources, and explicit tool definitions. For a developer seeking a turnkey, well-documented MCP server, this repository would score moderately, as it mainly provides setup details and basic use cases.

MCP Score

Our overall rating: 3/10 – The repository provides a basic bridge to Pulumi via MCP but lacks documentation, explicit resource/tool definitions, and licensing, making it less suitable for production or broader adoption without further development.