redwood
by douglas-gibbons
Overview
Provides a toolkit of helper functions for AI agents, enabling them to interact with the system via command execution, web scraping, and persistent data storage.
Installation
./server.shSecurity Notes
The `run_command` tool uses `subprocess.run(command, shell=True)`, which is a critical security vulnerability allowing for arbitrary command injection. This tool, if exposed to an untrusted agent or user, can lead to full system compromise. While the `mcp_client` prompts the user for execution by default for this server, this prompt can be overridden, and the underlying `shell=True` remains an inherent risk. The `web_scraper` tool could potentially be used for SSRF if the URL input is not adequately validated by the agent.
Similar Servers
mcp-client-for-ollama
An interactive Python client for connecting local Ollama LLMs to Model Context Protocol (MCP) servers, enabling advanced tool use and workflow automation.
mcp-server
Provides a Model Context Protocol (MCP) server for AI agents to search and retrieve curated documentation for the Strands Agents framework, facilitating AI coding assistance.
mcp-interviewer
A Python CLI tool designed to evaluate, test, and generate reports on Model Context Protocol (MCP) servers to ensure compatibility and quality for LLM agent use cases.
zeromcp
A minimal, pure Python Model Context Protocol (MCP) server for exposing tools, resources, and prompts via HTTP/SSE and Stdio transports.