AWS MCP Server

Overview

AWS MCP Server is a Model Context Protocol (MCP) server: A managed MCP server enabling AI agents to access AWS using docs, API calls, and SOP workflows. In practice that means any MCP-compatible AI assistant can call AWS MCP Server's tools directly — the model decides when to use them in a conversation or agent run.

It runs locally: the Python package mcp-proxy-for-aws (via uvx) speaks MCP over stdio on your machine. No credentials are required — it works out of the box. The current release is v1.0.0-preview.1.

AWS MCP Server is listed under Cloud Service on mcp.site and works with any MCP client — Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed and the rest of the ecosystem — using the install snippets below. If you maintain AWS MCP Server for aws, claim this listing to verify ownership, earn the Verified badge, and keep the details current.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "aws_mcp_server": {
      "command": "uvx",
      "args": [
        "mcp-proxy-for-aws"
      ]
    }
  }
}