# Pulumi (MCP Server)

> Search Pulumi stacks and resources, ask Neo and browse the Pulumi Registry

- Type: MCP server
- Publisher: Pulumi (official)
- Categories: DevOps & Cloud, Development
- Website: https://www.pulumi.com/docs/iac/guides/ai-integration/mcp-server/
- Transport: streamable-http
- Server URL: https://mcp.ai.pulumi.com/mcp
- Sign-in: oauth
- Listed: 2025-04-01

## About

Pulumi's hosted MCP server gives agents access to Pulumi Cloud stacks, resource search and policy violations, the Pulumi Registry schema for providers, and the Neo infrastructure agent. It is remote over Streamable HTTP; on first connect you paste a Pulumi access token and pick an organization, or headless clients send a bearer token.

## Install

1. **Connect it in ChatGPT** Turn on Developer mode in ChatGPT (Settings → Security and login), open Plugins, select + and paste https://mcp.ai.pulumi.com/mcp as the MCP server URL, then sign in with OAuth. Add it to a chat from the composer's tools menu.

2. **Or add it to Codex or the API**

   Codex CLI:

   ```bash
   codex mcp add pulumi --url https://mcp.ai.pulumi.com/mcp
   codex mcp login pulumi
   ```

   config.toml:

   ```toml
   [mcp_servers.pulumi]
   url = "https://mcp.ai.pulumi.com/mcp"
   ```

   Responses API:

   ```python
   import os
   from openai import OpenAI
   
   client = OpenAI()
   
   response = client.responses.create(
       model="gpt-6-astra",
       tools=[{
           "type": "mcp",
           "server_label": "pulumi",
           "server_url": "https://mcp.ai.pulumi.com/mcp",
           "authorization": os.environ["PULUMI_API_KEY"],
           "require_approval": "never",
       }],
       input="List my Pulumi stacks and when each was last updated",
   )
   print(response.output_text)
   ```

## Tools

- `get-stacks`
- `resource-search`
- `get-policy-violations`
- `neo-bridge`
- `list-resources`
- `get-resource`
- `get-function`
- `deploy-to-aws`

## Example prompts

- "List my Pulumi stacks and when each was last updated"
- "Find all S3 buckets across my stacks"
- "What properties does aws:rds:Instance accept?"
- "Are there any policy violations in the production stack?"

## Related

- [Chrome DevTools MCP](https://chatgptplugins.directory/mcp/chrome-devtools.md): Let coding agents control and debug a live Chrome browser
- [Playwright MCP](https://chatgptplugins.directory/mcp/playwright.md): Browser automation for agents via Playwright accessibility snapshots
- [GitHub](https://chatgptplugins.directory/mcp/github.md): Manage repos, issues, pull requests and Actions from your AI agent
- [Context7](https://chatgptplugins.directory/mcp/context7.md): Pull up-to-date, version-specific library docs into your coding agent
- [Supabase](https://chatgptplugins.directory/mcp/supabase.md): Manage Supabase databases, migrations, edge functions and logs
- [Stripe](https://chatgptplugins.directory/mcp/stripe.md): Query and act on your Stripe account and search Stripe docs from any agent

---
Source: https://chatgptplugins.directory/mcp/pulumi · Index: https://chatgptplugins.directory/llms.txt · Independent and community-run. Not affiliated with or endorsed by OpenAI. ChatGPT is a trademark of OpenAI.