Command Shell
A command execution server that provides secure shell command execution, directory navigation, and interactive program automation through pexpect integration. Built by Jon Allen, it features configurable command blocking and file access restrictions via TOML configuration, with safety controls that can be overridden when needed. The server includes tools for running shell commands with stdin support, changing directories with environment variable expansion, and automating interactive programs through expect/send sequences. Useful for system administration tasks, development workflows, and command-line tool interaction while maintaining security boundaries through customizable restrictions on dangerous commands and sensitive files.
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/jon2allen/mcp_command_serv
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve Command 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.