Wcgw: MCP server, setup and security

What Wcgw does

According to its repository: “Autonomous shell execution, computer control and coding agent for Mac.”

An MCP server gives an AI agent extra tools it calls during the conversation: the agent reads their description, decides to use them and gets the result back. Wcgw is listed under Other integrations, a category of 194 servers in the directory, where it ranks #22 by stars.

Topics declared by the repository: chatgpt, custom-gpt, llm-agent, llm-code, openai, shell.

Installing and connecting Wcgw

No package or remote server is declared in the official MCP registry: you install it from source, following the repository README.

Like any MCP server, you declare it in your client's configuration (Claude Desktop, Claude Code, Cursor, VS Code, Codex…): a name, the command that starts it or its URL, and any environment variables. The client then starts it and lists its tools. Project language: Python.

Security: what to check

An MCP server runs code with the rights you give it, and the model reads its tool descriptions: a malicious or compromised server can hijack the agent. Read the code, or pick a maintained and widely used server, before connecting it.

None of the risk signals we track (system access, secrets, missing licence, abandonment) applies to Wcgw. That does not replace reading the code.

Good practice: grant only the rights needed (least privilege), require human approval for irreversible actions, and run the AI agent security check.

Project activity and maintenance

Created on September 20, 2024, the rusiaaman/wcgw repository has 678 stars and 66 forks, with 4 open issues. It has more stars than 90% of the servers in the directory. Last change 1 month ago.

Stars measure attention, not quality: a recent, heavily promoted project can collect them fast, while a useful but niche server will have few.