PermShell
PermShell MCP is a TypeScript server that enables AI assistants to execute shell commands with explicit user permission through desktop notifications. Developed by Matteo Collina, it implements a security-focused approach where all commands require user approval via growl notifications that display the exact command and working directory for transparency. The server provides two main tools: 'execute-command' for running shell commands with permission safeguards and 'system-info' for retrieving system information without requiring explicit permission. It's particularly useful for scenarios where AI assistants need controlled access to the local system while maintaining strong security boundaries.
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
- security
- Source
- PulseMCP
- Repository
- github.com/mcollina/perm-shell-mcp
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve PermShell 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.