This MCP implementation, developed by rusiaaman, exposes the wcgw library's functionality via MCP. wcgw enables access the local shell and file system for task automation and code execution. It integrates with Docker to provide full control over a Linux environment, including mouse and keyboard input. It allows the AI to interact directly with the user's system, execute commands, manipulate files, and even control a virtualized desktop. The implementation is particularly useful for developers and power users who want to leverage LLM intelligence for system automation, code development, and complex multi-step tasks that require direct interaction with the operating system and applications.
Cognium trust score
50%
Tier
Unverified
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
Returns 7 tools: search_skills, get_skill, list_leaderboard, get_trust_breakdown, resolve_composition, plus the ChatGPT-connector search and fetch. Every tool is annotated read-only.
Resolve this skill directly via MCP tools/call get_skill.