CLI
This MCP server, developed by hdresearch, provides secure shell command execution capabilities for AI models. Built in Node.js, it integrates with Claude Desktop and enables AI assistants to run shell commands in a controlled environment. The implementation stands out through its focus on security, using command blacklisting, existence validation, and comprehensive error handling. By bridging AI models with the local shell, this server allows AI systems to interact with the file system, run utilities, and execute scripts. It is particularly useful for scenarios like system administration, development workflows, and building AI assistants that can leverage command-line tools while maintaining a strong security posture.
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/hdresearch/mcp-shell
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve CLI 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.