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.
@turbot
Basic information
Enable AI assistants to explore and query your Steampipe data!
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"steampipe": {
"command": "npx",
"args": [
"-y",
"@turbot/steampipe-mcp"
]
}
}
}Query cloud infrastructure, SaaS, APIs, code and more with SQL. Queries are read-only and must use PostgreSQL syntax. For best performance: limit columns requested, use materialized CTEs instead of joins. Trust the search path unless sure you need to specify a schema. Check available tables and columns before querying using steampipe_table_list and steampipe_table_show.
List all available Steampipe tables. Use schema and filter parameters to narrow down results.
Get detailed information about a specific Steampipe 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.
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.
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.
best_practices prompt to optimize LLM responses.status resource to verify connection state.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.
Add your Turbot Pipes connection string as an additional argument in the MCP configuration’s `args` array (e.g., `"postgresql://my_name:my_pw@workspace-name.usea1.db.pipes.turbot.com:9193/abc123"`).
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).
Yes, all queries are read‑only and use PostgreSQL syntax.
Yes, the `best_practices` prompt provides detailed guidance on SQL style, CTEs, optimization, and error handling. Run it first for best results.
MCP Toolbox for Databases is an open source MCP server for databases.

A free remote MCP server for The Living Bread. Bible passages read word for word from a stored public domain text with an evidence label, keyword search and cross references, real churches, gatherings and prayer groups w

Yuppsy MCP: build and publish real estate websites from your AI assistant. Yuppsy lets your AI assistant create live websites for real estate agents and individual property listings. You don't need a designer or any code

A good sequence diagram can solve almost any communication problem in engineering. Volley lets your agent write them as plain text, with the real request and response payloads on every arrow. It checks its own syntax wi
YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context
Comments