Project overview
agent-terminal lets an AI agent launch interactive CLI applications, capture their screen as ASCII text, and send keyboard input without a display. It can be used as an npm library or exposed through an MCP server for CLI testing, monitoring, and build automation. Built-in safeguards include command allowlists, workspace path validation, environment sanitization, input checks, and session limits.
Repository facts
- Primary language
- JavaScript
- License
- Not publicly identified
- Repository updated
- Jun 28, 2026
- Default branch
- main
Resource types
MCP serverAutomation
Use cases
AI and agent developmentDevOps and deploymentTesting and debugging
Platforms
Claude Code
Runtime
Command lineLocal
Protocols & integrations
Model Context Protocol
Capabilities
ObservabilityTool use