MCPLow riskUnclaimed

terminal-use

Lets AI agents drive a real terminal: type, press keys, click, read the screen, take screenshots.

computer-agent-labscomputer-agent-labs/terminal-useUpdated Oct 8, 2026

server.json

{
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "name": "io.github.computer-agent-labs/terminal-use",
  "description": "Lets AI agents drive a real terminal: type, press keys, click, read the screen, take screenshots.",
  "title": "terminal-use",
  "repository": {
    "url": "https://github.com/computer-agent-labs/terminal-use",
    "source": "github"
  },
  "version": "0.1.1",
  "icons": [
    {
      "src": "https://raw.githubusercontent.com/computer-agent-labs/terminal-use/main/docs/icon.png"
    }
  ],
  "packages": [
    {
      "registryType": "npm",
      "registryBaseUrl": "https://registry.npmjs.org",
      "identifier": "terminal-use",
      "version": "0.1.1",
      "runtimeHint": "npx",
      "transport": {
        "type": "stdio"
      }
    }
  ]
}

Permissions

DeclaredDetected
Runs code—node
Installs—npm:terminal-use@0.1.1
Runs install scripts—None
NetworkNoneNone
Needs credentialsNoneNone
Outside the workspace—None
Agent tools—None

Checks

Low risk · Nothing worth a warning was found.

Not reviewed by a person · Checked by rules; the model review is not switched on yet.

Versions

  1. #10.1.1latestOct 8, 2026