Terminal
This MCP server provides AI assistants with secure terminal command execution capabilities through both persistent shell sessions and non-persistent command execution, built by Iris using Go with cross-platform support for macOS and Linux. The implementation offers three execution modes: isolated commands with configurable timeouts, persistent shell sessions that maintain state between commands (allowing directory changes and environment variables to persist), and session management tools for listing and closing active shells. Built with both STDIO and StreamableHTTP transport support, comprehensive timeout controls, and non-root execution capabilities, it serves developers needing AI-powered terminal automation, teams requiring programmatic access to shell environments through conversational interfaces, and applications that need to execute system commands while maintaining shell context across multiple interactions.
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 2026-09-28.
Scan details: Circle-IR · 2026-09-28 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- file-system
- Source
- PulseMCP
- Repository
- github.com/iris-networks/terminal_mcp
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve 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.