Vet LLM-emitted shell commands BEFORE execution. 26 destructive-pattern rules / 8 families.
MCP server that vets LLM-emitted shell commands BEFORE execution — detects nested deep in chains, package-manager glob removal (), // filesystem destruction, / privilege blast, network-exfil via , chained /, and destructive ops. Sub-second, local, free, MCP-native — designed to be called inline by Claude Code / Cursor / Cline / OpenClaw before approving any agent-proposed command. Defensive…
Inferred from the transports this listing declares (stdio). A client not listed here hasn’t been ruled out — it just isn’t something Forge can confirm.
Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts.
Forge read 0 source files from the published package tarball and matched no MCP tool registrations. Extraction is pattern-based over shipped source: a server that builds its tool list at runtime, or that ships only bundled or minified code, registers nothing this can see. Treat it as “not detected”, not as “exposes none”.
MCP server that vets LLM-emitted shell commands BEFORE execution — detects nested deep in chains, package-manager glob removal (), // filesystem destruction, / privilege blast, network-exfil via , chained /, and destructive ops. Sub-second, local, free, MCP-native — designed to be called inline by Claude Code / Cursor / Cline / OpenClaw before approving any agent-proposed command. Defensive complement to MCP shell-execution servers (MCPShell, mcp-shell, mcp-bash). []( [](./tests) [](./LICENSE)…
Forge's dependency resolver reads npm metadata only, so this PyPI package has no resolved tree. That is a gap in coverage, not a clean bill of health.