Command Line
This MCP server allows AI assistants to execute common Unix/macOS terminal commands through a controlled and secure interface. It supports the top ~40 most used terminal commands with appropriate security measures. Features - Safe execution of common Unix/macOS commands - Security validation based on command type - Command categorization (read, write, system) - Interactive permission management - Session-based approval system - Configuration via environment variables or JSON file - Comprehensive command filtering and pattern matching - Support for command chaining via pipes (|), semicolons (;), and ampersands (&) - Claude Desktop compatibility mode with auto-approval - Detailed command metadata and help for AI assistants Read Commands ls, pwd, cat, less, head, tail, grep, find, which, du, df, file, sort, etc. Write Commands cp, mv, rm, mkdir, rmdir, touch, chmod, chown, etc. System Commands ps, top, htop, who, netstat, ifconfig, ping, etc.
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/andresthor/cmd-line-mcp
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve Command Line 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.