by yiwenlu66 · MCP Server · ★ 34
PiloTY PiloTY (PTY for your AI Copilot) is an MCP server that gives an agent a persistent, interactive terminal. If you have used Claude Code / Codex to run shell commands, you have probably hit the same wall: tool calls tend to be stateless. Each call starts "fresh", so environment variables disappear, interactive programs cannot be driven reliably, and long-running processes get cut off or orphaned while the agent is thinking. PiloTY exists to make the agent's terminal behave more like a human's: start something in a real terminal, come back later, and keep going.
| Stars | 34 |
| Forks | 5 |
| Language | Python |
| Category | MCP Server |
| Quality Score | 63.2415502153729/100 |
| Open Issues | 1 |
| Last Updated | 2026-04-23 |
| Created | 2025-06-28 |
| Platforms | cli, mcp, python |
| Est. Tokens | ~20k |
These tools work well together with PiloTY for enhanced workflows:
Explore other popular mcp server tools:
PiloTY is PiloTY: AI pilot for PTY operations via MCP - enables AI agents to control interactive terminals like a human. It is categorized as a MCP Server with 34 GitHub stars.
PiloTY is primarily written in Python. It covers topics such as ai-agent, automation, cli.
You can find installation instructions and usage details in the PiloTY GitHub repository at github.com/yiwenlu66/PiloTY. The project has 34 stars and 5 forks, indicating an active community.