MCP serverAI and agent development
agent-terminal
Control interactive command-line applications from AI agents without a visible terminal.
- Stars
- 11
- Forks
- 2
- Updated
- Updated Jun 28, 2026
Control interactive command-line applications from AI agents without a visible terminal.
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.
Resource types
Use cases
Platforms
Let MCP assistants navigate, act on, observe, and extract data from web pages.
Let agents discover and load relevant skills at runtime.
Runtime
Protocols & integrations
Capabilities
Public GitHub facts last synced Jul 10, 2026.
Retrieve compact, dependency-aware skill bundles from large SKILL.md libraries.
Run OpenCode models from Claude through MCP with asynchronous task control.