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.
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)
- In your main project's
.envfile, add:PULUMI_PROJECT_PATH=/absolute/path/to/your/project/infra - Set the
DOTENV_PATHenvironment variable in your shell profile:export DOTENV_PATH=/absolute/path/to/your/project/.envThis ensures the MCP server can always find and use your project's
.envfile, no matter where the MCP server is installed or run. Setting it in your shell profile makes it available in every terminal session. - 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
- Restart your MCP client (Cursor, Claude Desktop, etc.)
- Verify connection - you should see the server connect successfully
- Test tools - try using one of the available TimescaleDB tools:
timescale_create_servicetimescale_create_servicestimescale_delete_servicetimescale_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.jsfile exists and the path is absolute - Permission denied: Make sure the server directory is readable
- Environment variables: Confirm
PULUMI_PROJECT_PATHis 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):
- Install dependencies:
cd /path/to/tigerdata-pulumi-mcp-server npm install - 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
.envfile contains the correctPULUMI_PROJECT_PATH. - Make sure
DOTENV_PATHis set to your.envfile and is available in your shell (check withecho $DOTENV_PATH). - Restart your terminal after editing your shell profile.
- Make sure your
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
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。