command_execution
Run shell commands (rate limits, audit logs)
How to use it
command_execution is exposed by the AgentCrew MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the command_execution tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.
Install AgentCrew
pip install agentcrew-aiOther tools in AgentCrew (10)
Learn behavioral patterns from interactions
Full browser automation (navigate, click, form fill)
Read/write system clipboard
Read files, grep, analyze repo structure
Extract content from a URL
Write/modify files (search-replace blocks, backups)
Store and retrieve conversation context
Hand off tasks to other agents
Speak and listen (ElevenLabs or DeepInfra)
Search the web via Tavily