Shell Exec Mcp — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Shell Exec Mcp (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
MCP server for executing bash commands with background job support.
Run build commands: Execute npm run build, make, or other build tools and get the output.
File operations: Use find, grep, mv, rm, mkdir -p, stat etc. for file management.
Long-running tasks: Start servers or watch processes in background mode, check on them later.
System info: Run df -h, ps aux, env etc. to inspect the system state.
claude mcp add shell-exec-mcp -- npx -y shell-exec-mcpOr with HTTP transport:
# Start the server
MCP_TRANSPORT=http PORT=3000 npx -y shell-exec-mcp
# Add to Claude
claude mcp add --transport http shell-exec-mcp http://localhost:3000/mcp| Tool | Description |
|---|---|
execute | Run a bash command (with optional timeout and background mode) |
get_job_status | Check status of a background job |
Pull requests are welcomed on GitHub! To get started:
npm installnpm run test to run testsnpm run buildVersions follow the semantic versioning spec.
To release:
npm version <major | minor | patch> to bump the versiongit push --follow-tags to push with tags~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.