Steampipe Model Context Protocol (MCP) Server

Name: Steampipe Model Context Protocol (MCP) Server
Author: turbot

@turbot

代码仓库

关于 Steampipe Model Context Protocol (MCP) Server

Enable AI assistants to explore and query your Steampipe data!

#ai #mcp #steampipe #turbot-pipes #mcp-server

基本信息

分类

其他

许可证

Apache-2.0

运行时

node

传输方式

stdio

发布者

turbot

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "steampipe": {
      "command": "npx",
      "args": [
        "-y",
        "@turbot/steampipe-mcp"
      ]
    }
  }
}

工具

Query cloud and security logs with SQL.

List all available Steampipe tables.

Get detailed information about a specific table, including column definitions, data types, and descriptions.

List all Steampipe plugins installed on the system. Plugins provide access to different data sources like AWS, GCP, or Azure.

Get details for a specific Steampipe plugin installation, including version, memory limits, and configuration.

概览

What is Steampipe MCP Server?

The Steampipe MCP Server connects AI assistants like Claude to your cloud infrastructure data via Steampipe, enabling natural language exploration and analysis across AWS, Azure, GCP, and 100+ cloud services. It provides read‑only access to cloud and SaaS data for security, compliance, cost, and resource analysis.

How to use Steampipe MCP Server?

Install Node.js v16 or higher and have Steampipe running locally (steampipe service start) or a Turbot Pipes workspace. Add the server configuration to your AI assistant’s MCP config file (e.g., claude_desktop_config.json for Claude Desktop, ~/.cursor/mcp.json for Cursor). After restarting the assistant, run the best_practices prompt to teach the LLM how to work with Steampipe, then ask natural‑language questions about your infrastructure.

Key features of Steampipe MCP Server

Query cloud and security logs using SQL (PostgreSQL syntax).
List, filter, and inspect available Steampipe tables.
List and show details of installed Steampipe plugins.
Connect to local Steampipe or Turbot Pipes workspaces.
Provides a best_practices prompt to optimize LLM responses.
Exposes a status resource to verify connection state.

Use cases of Steampipe MCP Server

Explore cloud accounts and resources with natural language (e.g., “What AWS accounts can you see?”).
Generate infrastructure reports (e.g., “List EC2 instances with attached EBS volumes”).
Perform security analysis (e.g., “Find IAM users with unrotated access keys”).
Get compliance insights (e.g., “Show EC2 instances not complying with tagging standards”).
Analyze risks (e.g., “Check S3 buckets for public access and encryption”).

FAQ from Steampipe MCP Server

What prerequisites are needed?

Node.js v16 or higher is required. For local use, Steampipe must be installed and running (steampipe service start). For cloud use, a Turbot Pipes workspace and connection string are needed.

How do I connect to Turbot Pipes instead of local Steampipe?

Add your Turbot Pipes connection string as an additional argument in the MCP configuration’s args array (e.g., "postgresql://my_name:[email protected]:9193/abc123").

What tools does the server provide?

The server provides five tools: steampipe_query (run SQL), steampipe_table_list (list tables), steampipe_table_show (details of a table), steampipe_plugin_list (list installed plugins), and steampipe_plugin_show (details of a plugin).