Mac Shell
Mac Shell MCP Server enables secure execution of macOS terminal commands through ZSH shell with a built-in security system that categorizes commands as safe, requiring approval, or forbidden. It features a pre-configured whitelist of common commands, an approval workflow for potentially dangerous operations, and comprehensive command management tools. Written in TypeScript and designed to work with Roo Code and Claude Desktop, it can be installed locally or run via npx, making it ideal for AI assistants that need controlled access to the macOS terminal while maintaining security through command whitelisting and explicit approval mechanisms.
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
- security
- Source
- PulseMCP
- Repository
- github.com/cfdude/mac-shell-mcp
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Mac Shell 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.