Pulumi is a Cloud Platforms MCP server that lets Claude Code, Cursor, Windsurf and any MCP-compatible AI agent cloud infrastructure with Pulumi Automation API. Install in 1 minute with mcpizy install pulumi.
Cloud Platforms
Cloud infrastructure with Pulumi Automation API
mcpizy install puluminpx -y @pulumi/mcp-serverContainer management via Portainer
Deploy containerized applications to Google Cloud Run. Serverless container hosting.
Query Amazon Bedrock Knowledge Bases using natural language. RAG over your enterprise data.
Infrastructure as Code with HashiCorp Terraform
If Pulumi doesn't fit your stack, these Cloud Platforms MCP servers solve similar problems.
The Pulumi MCP server is an Cloud Platforms Model Context Protocol server that lets Claude Code, Cursor, Windsurf, VS Code with Copilot, and other MCP-compatible AI agents cloud infrastructure with Pulumi Automation API. It exposes Pulumi's capabilities as tools the AI can call directly from your editor or CLI.
The fastest way is the MCPizy CLI: run `mcpizy install pulumi` and MCPizy will add the server to your `.claude.json` automatically. You can also install it manually by adding an entry under `mcpServers` in `.claude.json` with the command `npx -y @pulumi/mcp-server` and restarting Claude Code.
Yes. The Pulumi MCP server is free and open source (see the GitHub repository linked on this page). You may still need a Pulumi account or API key to connect the server to the underlying service, but the MCP layer itself has no MCPizy subscription cost.
Yes. Any MCP-compatible client works — including Claude Code, Claude Desktop, Cursor (via `.cursor/mcp.json`), Windsurf, VS Code with Copilot Chat, and custom agents built on the MCP SDK. The same install command targets all of them; only the config file path differs.
Once installed, your AI agent can cloud infrastructure with Pulumi Automation API directly inside your conversation. Typical use cases include asking Claude Code or Cursor to run Pulumi operations, inspect results, chain Pulumi with other MCP servers (see our Workflow Recipes), and automate repetitive cloud platforms tasks without leaving your editor.