Skip to content

recourse-cli

MCP server for AI agents to evaluate consequences before destructive actions. Analyzes Terraform plans, shell commands, and MCP tool calls.

32
Weekly Downloads
automate.devops.runbooks#mcp#mcp-server#model-context-protocol#ai-agents#terraform#infrastructure#consequence-analysis#blast-radius#safety#claude

Install recourse-cli in your MCP client

recourse-cli is a Model Context Protocol server. Add it to your MCP client config once, restart, and the server's tools become available to your AI assistant. The same JSON snippet below works across all four major clients — only the config file path differs.

  1. Locate your client's MCP config file.
    • Cursor: ~/.cursor/mcp.json
    • Claude Desktop (macOS): ~/Library/Application Support/Claude/claude_desktop_config.json
    • Claude Desktop (Windows): %APPDATA%\Claude\claude_desktop_config.json
    • VS Code: Settings → Extensions → MCP
    • Windsurf: Settings → MCP Servers
  2. Add recourse-cli to the mcpServers map — paste the snippet below into your config file. If you already have other MCP servers, merge the entry into the existing mcpServers object.
  3. Restart your client so it picks up the new server.
  4. Verify — ask the assistant to list available tools; recourse-cli's tools should appear.
{
  "mcpServers": {
    "recourse-cli": {
      "command": "npx",
      "args": [
        "-y",
        "recourse-cli"
      ]
    }
  }
}

Install recourse-cli in Cursor

Open ~/.cursor/mcp.json in your editor, paste the snippet above into mcpServers, save, and restart Cursor. recourse-cli will show up in the assistant's tool list on next launch.

Install recourse-cli in Claude Desktop (macOS)

Open ~/Library/Application Support/Claude/claude_desktop_config.json in your editor, paste the snippet above into mcpServers, save, and restart Claude Desktop (macOS). recourse-cli will show up in the assistant's tool list on next launch.

Install recourse-cli in Claude Desktop (Windows)

Open %APPDATA%\Claude\claude_desktop_config.json in your editor, paste the snippet above into mcpServers, save, and restart Claude Desktop (Windows). recourse-cli will show up in the assistant's tool list on next launch.

Install recourse-cli in VS Code

Open Settings → Extensions → MCP in your editor, paste the snippet above into mcpServers, save, and restart VS Code. recourse-cli will show up in the assistant's tool list on next launch.

npm package: recourse-cli

Transport

recourse-cli supports the following MCP transports. Most AI clients use stdio by default for locally-installed servers.

stdio

From the recourse-cli README

<p align="center"> <picture> <source media="(prefers-color-scheme: dark)" srcset="https://recourseos.com/brand/logo-mark-light-512.png"> <source media="(prefers-color-scheme: light)" srcset="https://recourseos.com/brand/logo-mark-512.png"> <img src="https://recourseos.com/brand/logo-mark-512.png" alt="RecourseOS" width="120" /> </picture> </p> <h1 align="center">RecourseOS</h1> <p align="center"> <strong>Consequence layer for AI agents</strong><br> Check recoverability before destructive actions </p> <p align="center"> <a href="https://www.npmjs.com/package/recourse-cli"><img src="https://img.shields.io/npm/v/recourse-cli.svg" alt="npm version"></a> <a href="https://github.com/recourseOS/recourse/blob/main/LICENSE"><img src="https://img.shields.io/badge/license-M

Other Model Context Protocol servers in the same space as recourse-cli. Each one adds different capabilities to your AI assistant — pick based on the data sources or workflows you need.

Browse the full MCP server directory or use Stork's one-line install to let your agent pick the right server automatically.