Steampipe MCP Server

Steampipe MCP server to query cloud infrastructure, SaaS, code and more with SQL using AI.

Local serverstdio

What is the Steampipe MCP server?

Connect Steampipe to Claude, Cursor or any other MCP client and it stops being a tab you switch to. Steampipe MCP server to query cloud infrastructure, SaaS, code and more with SQL using AI. The steampipe mcp server is what makes that connection.

What the server does

Unlock the power of AI-driven infrastructure analysis with Steampipe! This Model Context Protocol server seamlessly connects AI assistants like Claude to your cloud infrastructure data, enabling natural language exploration and analysis of your entire cloud estate.

Available tools

The toolset is worth reading before you wire it up, because it tells you what the integration is really for:

  • steampipe_query — Query cloud and security logs with SQL
  • Input — sql (string): The SQL query to execute using PostgreSQL syntax
  • steampipe_table_list — List all available Steampipe tables
  • steampipe_table_show — Get detailed information about a specific table, including column definitions, data types, and descriptions
  • steampipe_plugin_list — List all Steampipe plugins installed on the system. Plugins provide access to different data sources like AWS, GCP, or Azure
  • steampipe_plugin_show — Get details for a specific Steampipe plugin installation, including version, memory limits, and configuration
  • Prerequisites — The Prerequisites tool exposed by this server
  • Configuration — Add Steampipe MCP to your AI assistant's configuration file:
  • Tools — The Tools tool exposed by this server
  • Prompts — The Prompts tool exposed by this server
  • Resources — This resource enables AI tools to check and verify the connection status to your Steampipe instance
  • Testing — To test your local development build with AI tools that support MCP, update your MCP configuration to use the local dist/index.js instead of the npm

Credentials and setup notes

  • Node.js v16 or higher (includes npx) - For local use: Steampipe installed and running (steampipe service start) - For Turbot Pipes: A Turbot Pipes workspace and connection string

Installation

The server ships on npm as @modelcontextprotocol/inspector, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.

Where it fits

Plenty of database access servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Steampipe's toolset — steampipe_query, Input, steampipe_table_list and 9 more — is a fair guide to whether it matches your workflow. It is maintained by e-gineer; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Worth knowing first

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 12 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Steampipe.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
steampipe_queryQuery cloud and security logs with SQL.
Inputsql (string): The SQL query to execute using PostgreSQL syntax
steampipe_table_listList all available Steampipe tables.
steampipe_table_showGet detailed information about a specific table, including column definitions, data types, and descriptions.
steampipe_plugin_listList all Steampipe plugins installed on the system. Plugins provide access to different data sources like AWS, GCP, or Azure.
steampipe_plugin_showGet details for a specific Steampipe plugin installation, including version, memory limits, and configuration.
PrerequisitesThe Prerequisites tool exposed by this server.
ConfigurationAdd Steampipe MCP to your AI assistant's configuration file:
ToolsThe Tools tool exposed by this server.
PromptsThe Prompts tool exposed by this server.
ResourcesThis resource enables AI tools to check and verify the connection status to your Steampipe instance.
TestingTo test your local development build with AI tools that support MCP, update your MCP configuration to use the local dist/index.js instead of the npm package. For example:

How to install the Steampipe MCP server

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

Configuration as documented by the project. Restart the client after saving.

Configuration

  • Node.js v16 or higher (includes npx) - For local use: Steampipe installed and running (steampipe service start) - For Turbot Pipes: A Turbot Pipes workspace and connection string

Example prompts to try

  • Use Steampipe to steampipe query.
  • Use Steampipe to Input.
  • Use Steampipe to steampipe table list.

Frequently asked questions

It connects Steampipe to MCP-compatible AI assistants such as Claude and Cursor, exposing 12 tools (steampipe_query, Input, steampipe_table_list, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Steampipe directly.