awslabs.aws-api-mcp-server

Level ALocal

Model Context Protocol (MCP) server for interacting with AWS

Overview

AWS API MCP Server lets AI assistants interact with AWS services and resources through AWS CLI commands, enabling users to create, update, and manage AWS resources and helping select appropriate CLI commands and access the latest AWS API features released after a model's knowledge cutoff. It requires configured AWS credentials and supports stdio and HTTP modes. Note: it is superseded by the official AWS MCP server; a migration guide is available.

⭐ 9.9kDevOps & DeploymentPythonRepo ↗Updated 2026-11-02

Installation

MCP client config (paste into mcp.json)

{
  "mcpServers": {
    "awslabs-mcp-src-aws-api-mcp-server": {
      "command": "uvx",
      "args": [
        "awslabs.aws-api-mcp-server@latest"
      ],
      "env": {
        "FASTMCP_LOG_LEVEL": "ERROR",
        "AWS_REGION": "us-east-1"
      }
    }
  }
}

Agent install prompt

Copy and paste into Cursor / Claude / other agents to install this MCP for you

Please read this MCP repository and install it into my current environment:
https://github.com/awslabs/mcp/tree/main/src/aws-api-mcp-server

Known working client config (can write into mcp.json):
{
  "mcpServers": {
    "awslabs-mcp-src-aws-api-mcp-server": {
      "command": "uvx",
      "args": [
        "awslabs.aws-api-mcp-server@latest"
      ],
      "env": {
        "FASTMCP_LOG_LEVEL": "ERROR",
        "AWS_REGION": "us-east-1"
      }
    }
  }
}

Please: 1) check README for deps and env vars; 2) write config for my client; 3) if secrets are missing, tell me what to fill — do not invent values.

Related servers