Le catalogue réel des outils pour IA

POSIX shell quote shape, input discarded

Turns vague automation requests into tool stacks, prompts, QA checks, and human boundaries.

Let agents use the shell like a human.

Execute bash commands with background job support.

Scheduled HTTP requests and shell commands with retries, timeouts, and webhook alerts.

A private persistent computer: files and a bash shell that survive between runs.

Persistent Linux computers for AI agents: desktop, signed-in browser, vault, apps and shell.

Remote shell and detached long-running jobs on your own machines — no SSH, open ports or VPN.

Run YAML-defined shell command stacks as MCP tools

I run shell commands on your private cloud environment (bash, sh, zsh)

Jev judgments for agents: injection scanning, shell risk gating, ranking

Standalone MCP filesystem tools server — view, edit, shell, workdir.

Audit Dockerfiles for root users, baked-in secrets, curl-pipe-shell and unpinned base images.

Safe shell argument escaping for bash, cmd.exe, and PowerShell.

Undo a coding agent turn, including shell commands and untracked files.

Lightweight MCP server providing terminal access (SSH & local shells) for AI assistants.

Sophisticated bash command MCP server that runs and manages shell execution.

Sandboxed shell exec for MCP clients: run untrusted agent commands in a gVisor container.

Injects secrets into shell commands at exec time; plaintext never reaches the LLM context

Stateful, structured, safe shell sessions for AI agents over local, SSH, and Docker.