PulumiをChatGPT、Claude、Geminiに接続

• 01 / 03Pulumiのデプロイ履歴を監査する方法
• 02 / 03スタックの整理方法
• 03 / 03スタック出力を取得する方法

最速日

760ms

最遅日

1172ms

14日間の傾向

遅延傾向+22%

Pulumi Connector

準備完了です。MCPクライアントを選択し、セットアップ手順に従ってください。

コネクタリンクhttps://edge.vinkius.com/vk_preview_v2N5nlYKKcBMg7t6tvswP5zOuY1KsfB14QgLHciO/mcpコピー

Claude Desktop

以下の手順で数秒で接続できます。

1. 1In Claude Desktop, open Settings → Connectors.
2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
3. 3Click Add and start a new chat — Pulumi capabilities are ready to use.

設定 · claude_desktop_config.jsonコピー

{
  "mcpServers": {
    "pulumi-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_v2N5nlYKKcBMg7t6tvswP5zOuY1KsfB14QgLHciO/mcp"
    }
  }
}

• Claude
• ChatGPT
• Cursor
• VS Code
• Windsurf
• Claude Code
• JetBrains
• Cline

各クライアントの手順ガイドはこちらです。 接続方法

Claude向けのガイド付きセットアップ？ PulumiをClaudeや他のAIに設定する

このConnectorが対応するすべてのAIクライアントを見る ↑

• 01

  DevOpsエンジニア

  コンソールを開くことなく、スタックの状態確認やデプロイ履歴のレビュー、出力値の確認を迅速に行いたい方。

• 02

  プラットフォームチーム

  インフラの変更を監査し、デプロイ成功率を追跡したり、組織横断的なスタックタグを管理したりする方。

• 03

  開発者

  利用可能なスタックを素早く探し、エクスポートされたエンドポイントを確認し、会話を通じてリソースのプロビジョニング状況を検証したい方。

• 01

  How do I connect my Pulumi account?

  You subscribe to the MCP on Vinkius and enter your Pulumi Access Token. Once connected, your AI client can immediately start interacting with your Pulumi organization.

• 02

  Which AI clients can I use with this MCP?

  You can use any MCP-compatible client, including Claude, Cursor, Windsurf, and VS Code.

• 03

  Can I delete stacks using my AI agent?

  Yes, you can use the delete_stack capability. Note that the stack must be empty or you must enable force deletion, and this action cannot be undone.

• 04

  What kind of information can the agent retrieve from my stacks?

  The agent can retrieve stack details, deployment history, resource counts, and exported outputs like IP addresses and URLs.

• 05

  Is my Pulumi token stored securely?

  Vinkius manages your credentials and keeps the connection running so you don't have to handle manual configuration every time you start a session.

• 06

  How do I get a Pulumi Access Token?

  Log in to the Pulumi Console, go to Account Settings > Access Tokens, click Create Token, give it a name and copy the token immediately. it starts with pul_ and won't be shown again.

• 07

  What is a Pulumi stack?

  A stack is an isolated, independently configurable instance of your Pulumi program. Stacks typically represent different environments like dev, staging and prod. Each stack has its own configuration, state, outputs and deployment history. Use list_stacks to discover all stacks in an organization.

• 08

  Can I see the deployment history of a stack?

  Yes! Use list_deployments with the org name, project name and stack name. It returns the update history showing version number, status (succeeded, failed, in-progress), start/end time and resource change counts. Use get_deployment with a specific version for detailed logs and error messages.

• 09

  Can I view the outputs of a stack?

  Yes! Use get_stack_outputs with the org name, project name and stack name. It returns all exported output values from the latest successful deployment, such as URLs, IP addresses, resource IDs and connection strings. This is useful for discovering endpoint addresses after infrastructure deployment.

• 

  Civo (Cloud-native Kubernetes Cloud Provider API) AIコネクタ

  Manage Civo cloud infrastructure — provision Kubernetes clusters, control compute instances, and monitor usage

  表示
• 

  JD Cloud Infrastructure AIコネクタ

  Manage JD Cloud supply-chain infrastructure from your AI. Control VMs, disks, databases, and monitor resource

  表示
• 

  Clever Cloud (Developer PaaS API) AIコネクタ

  Manage your Clever Cloud infrastructure—apps, add-ons, and deployments—directly from your AI agent.

  表示
• 

  Flightcontrol (AWS PaaS Deployments) AIコネクタ

  Deploy and manage AWS infrastructure via Flightcontrol — list projects, manage environments, and scale service

  表示

おすすめ

• 

  Terraform Cloud (HCP) AIコネクタ

  Manage infrastructure lifecycle via Terraform Cloud (HCP) — list organizations, manage workspaces, trigger run

  表示
• 

  Cloudflare AIコネクタ

  AI edge infrastructure: manage Workers, KV, D1, R2, routes, and deployments via agents.

  表示
• 

  Cloudify AIコネクタ

  Orchestrate cloud infrastructure via Cloudify — manage blueprints, deployments, and monitor workflow execution

  表示
• 

  Render AIコネクタ

  Equip your AI to orchestrate cloud infrastructure, manage service deployments, and execute scaling operations

  表示