TigerData Pulumi MCP Server

TigerData Pulumi MCP Server

An MCP server for managing TigerData Cloud services via Pulumi automation, enabling operations like creating, listing, and deleting TimescaleDB services through natural language.

Category
访问服务器

README

TigerData Pulumi MCP Server

Note: If you are using this MCP server via an MCP client (such as Cursor), you do not need to run or manage the server process manually. The client will handle all communication with the MCP server for you.

This project provides a server interface for managing TigerData Cloud services using Pulumi automation.

Quick Setup for MCP Clients (e.g., Cursor)

  1. In your main project's .env file, add:
    PULUMI_PROJECT_PATH=/absolute/path/to/your/project/infra
    
  2. Set the DOTENV_PATH environment variable in your shell profile:
    export DOTENV_PATH=/absolute/path/to/your/project/.env
    

    This ensures the MCP server can always find and use your project's .env file, no matter where the MCP server is installed or run. Setting it in your shell profile makes it available in every terminal session.

  3. Configure your MCP client (e.g., Cursor) as needed (e.g., with mcp.json).

That's it! You can now use all MCP features in your client, and the MCP server will automatically use your configuration.

MCP Configuration Setup

For Cursor IDE

Create or update your MCP configuration file at ~/.cursor/mcp.json:

{
  "mcpServers": {
    "tigerdata-pulumi": {
      "command": "node",
      "args": [
        "/absolute/path/to/tigerdata-pulumi-mcp-server/dist/index.js"
      ],
      "env": {
        "PULUMI_PROJECT_PATH": "/absolute/path/to/your/project/infra"
      }
    }
  }
}

Example paths:

  • If your server is at: /Users/username/projects/tigerdata-pulumi-mcp-server/
  • And your Pulumi infra is at: /Users/username/projects/my-project/infra/
  • Your config would be:
{
  "mcpServers": {
    "tigerdata-pulumi": {
      "command": "node",
      "args": [
        "/Users/username/projects/tigerdata-pulumi-mcp-server/dist/index.js"
      ],
      "env": {
        "PULUMI_PROJECT_PATH": "/Users/username/projects/my-project/infra"
      }
    }
  }
}

For Other MCP Clients

Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "tigerdata-pulumi": {
      "command": "node",
      "args": ["/path/to/tigerdata-pulumi-mcp-server/dist/index.js"],
      "env": {
        "PULUMI_PROJECT_PATH": "/path/to/your/project/infra"
      }
    }
  }
}

Anthropic's Inspector (Debugging Tool)

Add this to your MCP config for debugging:

{
  "mcpServers": {
    "inspector": {
      "command": "npx",
      "args": ["--yes", "@anthropic-ai/inspector"]
    }
  }
}

Configuration Options

Option Description Required Default
command Command to run the server Yes node
args Array of command arguments Yes ["/path/to/dist/index.js"]
env.PULUMI_PROJECT_PATH Path to your Pulumi infrastructure directory Yes None

After Configuration

  1. Restart your MCP client (Cursor, Claude Desktop, etc.)
  2. Verify connection - you should see the server connect successfully
  3. Test tools - try using one of the available TimescaleDB tools:
    • timescale_create_service
    • timescale_create_services
    • timescale_delete_service
    • timescale_list_services

Troubleshooting MCP Connection

  • "No tools or prompts" error: Ensure the server path in your config is correct
  • Server not found: Verify the dist/index.js file exists and the path is absolute
  • Permission denied: Make sure the server directory is readable
  • Environment variables: Confirm PULUMI_PROJECT_PATH is set correctly

Advanced: Running the MCP Server Manually

If you ever need to run the MCP server as a standalone process (for development or debugging):

  1. Install dependencies:
    cd /path/to/tigerdata-pulumi-mcp-server
    npm install
    
  2. Start the server:
    npm start
    

Initializing or Selecting a Pulumi Stack (from the terminal)

You can initialize or select your Pulumi stack directly from your infra directory:

cd /absolute/path/to/your/project/infra
pulumi stack init dev   # (or pulumi stack select dev if it already exists)
pulumi up

Troubleshooting

  • Error: Invalid workDir passed to local workspace:
    • Make sure your .env file contains the correct PULUMI_PROJECT_PATH.
    • Make sure DOTENV_PATH is set to your .env file and is available in your shell (check with echo $DOTENV_PATH).
    • Restart your terminal after editing your shell profile.

Example .env.example

# Path to your Pulumi infra directory
# PULUMI_PROJECT_PATH=/absolute/path/to/your/project/infra

This setup allows you to use the MCP server with any project structure, making it flexible and user-friendly for all users.

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选