PTY Terminal
This MCP tool server, developed by David Wurtz at Qodo AI, provides a stateful terminal interface for AI interactions. Built with Python and leveraging libraries like pexpect, it offers a persistent environment for command execution and output capture. The implementation focuses on maintaining session state across multiple interactions, enabling complex, multi-step operations. By providing a stateful terminal, this server allows for sophisticated scenarios like running long-running processes, interactive debugging, or step-by-step system configuration. It's particularly useful for AI assistants or applications that need to perform sequential terminal operations or maintain context across multiple commands.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- other
- Source
- PulseMCP
- Repository
- github.com/qododavid/pty-mcp
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve PTY Terminal from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.