poly-cloud-mcp
Verified Safeby hyperpolymath
Overview
Provides a unified Model Context Protocol (MCP) server for managing cloud resources across AWS, Google Cloud, Azure, and DigitalOcean, primarily enabling AI assistants to interact with these providers via their CLI tools.
Installation
deno run --allow-run --allow-read --allow-write --allow-env --allow-net main.jsEnvironment Variables
- AWS_ACCESS_KEY_ID
- AWS_SECRET_ACCESS_KEY
- AWS_REGION
- DIGITALOCEAN_ACCESS_TOKEN
Security Notes
This MCP server explicitly requires Deno's `--allow-run` permission to execute external cloud CLI commands (aws, gcloud, az, doctl). This grants the server (and any client controlling it) the ability to run arbitrary commands on the host system. The security boundary is therefore the host's configured cloud CLI credentials. The project transparently warns about this and recommends using minimal IAM permissions, separate credentials, avoiding admin access, and reviewing tool calls. No direct hardcoded secrets or 'eval' are observed in the provided code, but the inherent nature of wrapping powerful CLIs with `--allow-run` demands extreme caution.
Similar Servers
mcpm.sh
MCPM is a command-line tool for managing Model Context Protocol (MCP) servers, enabling discovery, installation, execution, sharing, and integration with various MCP clients.
cli
The Smithery CLI is a developer tool for installing, managing, building, running, and deploying Model Context Protocol (MCP) servers and integrating them with various AI clients.
aws-mcp-server
The AWS MCP Server allows AI assistants to execute AWS CLI commands and access AWS environment context, providing a powerful interface for cloud management and automation.
mcp-use-cli
An interactive command-line interface (CLI) tool for connecting to and interacting with Model Context Protocol (MCP) servers using natural language, acting as an AI client that orchestrates LLM responses with external tools.