Skip to content
MCP-Bridge
AI & ML

Amazon Augmented AI Runtime MCP Config

<p>Amazon Augmented AI (Amazon A2I) adds the benefit of human judgment to any machine learning application. When an AI application can't evaluate data with a high degree of confidence, human reviewers can take over. This human review is called a human review workflow. To create and start a human rev

Config URL

Use this URL in any MCP-compatible client to fetch the config automatically.

https://mcp-bridge.pages.dev/config/amazonaws-com-sagemaker-a2i-runtime.json

Configuration JSON

Use curl https://mcp-bridge.pages.dev/config/amazonaws-com-sagemaker-a2i-runtime.json to fetch programmatically.

{
  "mcpServers": {
    "amazonaws-com-sagemaker-a2i-runtime": {
      "command": "npx",
      "args": ["-y","@mcp/amazonaws-com-sagemaker-a2i-runtime"],
      "env": {
      "AMAZON_AUGMENTED_AI_RUNTIME_API_KEY": "your_amazon_augmented_ai_runtime_api_key"
}
    }
  }
}

How to Use

Claude Desktop

Paste the config JSON into your claude_desktop_config.json.

Full instructions →

Cursor

Go to Cursor Settings → MCP Servers → Add with the JSON above.

CLI / curl

Fetch the config programmatically:

curl https://mcp-bridge.pages.dev/config/amazonaws-com-sagemaker-a2i-runtime.json

Environment Variables

AMAZON_AUGMENTED_AI_RUNTIME_API_KEY

Replace your_amazon_augmented_ai_runtime_api_key with your actual amazon augmented ai runtime api key

Endpoints

GET/human-loops/{HumanLoopName}

DescribeHumanLoop

DELETE/human-loops/{HumanLoopName}

DeleteHumanLoop

GET/human-loops#FlowDefinitionArn

ListHumanLoops

POST/human-loops

StartHumanLoop

POST/human-loops/stop

StopHumanLoop