pulsemcp verified Safe content atomic mcp-remote

Super Shell

Super Shell MCP Server enables secure execution of shell commands across Windows, macOS, and Linux platforms with automatic platform detection and shell selection. Built with TypeScript using the Model Context Protocol SDK, it implements a robust security model with command whitelisting at three levels (safe, requires approval, forbidden) and provides tools for command execution, whitelist management, and platform information retrieval. The server is designed for integration with AI assistants through Roo Code and Claude Desktop, making it valuable for workflows requiring controlled access to the local system's shell capabilities while maintaining security through explicit approval mechanisms.

Cognium trust score
88%
Tier
Verified

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
Author type
human
Last scanned
2026-09-19
Updated
2026-09-19
View source Find related skills

Use via MCP

MCP

Resolve Super 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
Swap --scope user for --scope project to commit it to .mcp.json.

Search SkillsRegistry