mcpserve
by mark-oori
Overview
Serve Deep Learning models and provide shell execution capabilities, with Docker containerization and Ngrok connectivity.
Installation
docker-compose up -dEnvironment Variables
- APP_NAME
- APP_DEBUG
- APP_LOG_LEVEL
- APP_PORT
- MCP_API_KEY
Security Notes
CRITICAL SECURITY VULNERABILITY: The `shell_command` function (exposed as an API tool) uses `subprocess.check_output(command, shell=True)`. This allows arbitrary shell command injection if the `command` input is not sanitized, leading to Remote Code Execution (RCE). Furthermore, the API key authentication middleware (`'middleware': middleware`) is commented out by default, making the server publicly accessible and vulnerable to any caller without authentication.
Similar Servers
arcade-mcp
A framework and collection of toolkits for building and deploying AI agent servers that integrate with various external services.
mcp_massive
An AI agent orchestration server, likely interacting with LLMs and managing multi-agent workflows.
ssh-mcp-server
Enables AI assistants to securely execute remote SSH commands and perform file transfers on target servers via the Model Context Protocol (MCP).
mcp-ssh-manager
Manages remote SSH servers via the Model Context Protocol (MCP), enabling AI assistants like Claude Code and OpenAI Codex to execute commands, transfer files, monitor health, and automate DevOps tasks.