Amazon Augmented AI Runtime MCP Server
Amazon Augmented AI (Amazon A2I) Runtime is a specialized API service provided by Amazon Web Services (AWS) that enables developers to seamlessly integrate human review workflows into their machine learning applications.
Quick Start Summary
The Amazon Augmented AI Runtime MCP server is a Model Context Protocol bridge that connects AI assistants — including Claude Desktop, Cursor, Windsurf, and VS Code Copilot — to the Amazon Augmented AI Runtime API through natural language. It exposes 5 API endpoints as callable tools, such as DescribeHumanLoop, DeleteHumanLoop, ListHumanLoops, and more. No authentication is required — setup takes approximately 30 seconds. The server uses STDIO transport and can be installed by running npx -y @mcp/amazonaws-com-sagemaker-a2i-runtime. This integration is sourced from the auto Amazon Augmented AI Runtime OpenAPI specification (v2019-11-07) and has a quality score of 40/99 (fair documentation coverage).
Server Details
- Category
- AI & ML
- Authentication
- None
- Endpoints
- 5 operations
- Transport
- STDIO
- Spec Version
- v2019-11-07
- Install Command
npx -y @mcp/amazonaws-com-sagemaker-a2i-runtime
Environment Variables
AMAZON_AUGMENTED_AI_RUNTIME_API_KEYExample: your_amazon_augmented_ai_runtime_api_key
Top Endpoints
/human-loops/{HumanLoopName}DescribeHumanLoop
/human-loops/{HumanLoopName}DeleteHumanLoop
/human-loops#FlowDefinitionArnListHumanLoops
/human-loopsStartHumanLoop
/human-loops/stopStopHumanLoop
One-Click Install
Copy the snippet for your MCP client and paste it in — zero editing required.
Claude Desktop
Add to claude_desktop_config.json
{
"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"
}
}
}
}Cursor
Settings → MCP Servers → Add
{
"mcpServers": {
"amazonaws-com-sagemaker-a2i-runtime": {
"url": "https://mcpbridge.org/config/amazonaws-com-sagemaker-a2i-runtime.json"
}
}
}Saves as .cursor/mcp.json in the download. Move it to your project root.
VS Code
Use with MCP extension
{
"mcpServers": {
"amazonaws-com-sagemaker-a2i-runtime": {
"url": "https://mcpbridge.org/config/amazonaws-com-sagemaker-a2i-runtime.json"
}
}
}Endpoints Explorer
Search and browse the 5 operations supported by this server.
Multi-Language Code Examples
Executable code snippets for calling Amazon Augmented AI Runtime endpoints in curl, TypeScript, or Python.
curl -X GET "https://api.apis.guru/v2/specs/amazonaws.com/sagemaker-a2i-runtime/2019-11-07/human-loops/{HumanLoopName}" \
-H "Content-Type: application/json" \
# No auth requiredManual Configuration
Directly add this block to your JSON config file, or use the hosted config registry URL.
{
"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"
}
}
}
}Authentication Details
No authentication required. This MCP server runs out-of-the-box.
Documentation Links
Error Handling & HTTP Status Code Matrix
Common status codes, error causes, and resolution steps when invoking Amazon Augmented AI Runtime endpoints.
400 Bad RequestCause: Malformed payload parameters or missing required fields.
Resolution: Verify request schema in Endpoints tab before calling tool.
401 UnauthorizedCause: Missing or invalid API key credentials.
Resolution: Set environment variable in MCP client config under env object.
403 ForbiddenCause: Insufficient scope permissions for requested resource.
Resolution: Verify key permissions in developer dashboard.
404 Not FoundCause: Resource URL path or requested entity ID does not exist.
Resolution: Check path variables and parameters.
429 Rate Limit ExceededCause: API rate limit quota exceeded.
Resolution: Implement exponential backoff retry in tool call.
500 Internal ErrorCause: Upstream server runtime fault.
Resolution: Inspect STDIO stderr output for log trace.
Quality Score
Checked against our protocol-compliance rules.
Specification Version: v2019-11-07
Page compiled on: June 13, 2026
Own this API?
Verify ownership of this listing to control the description, configuration details, and documentation links. Choose between free manual verification or instant premium placement.
Option 1: Free Verification
Slow manual review. Requires creating a GitHub issue with verified documentation or domain verification.
- • Verified badge on page
- • Standard search sorting
- • 2-3 business days review
Option 2: Featured Upgrade($9/mo)
Instant verification plus premium styling, featured badges, and directory placement boost.
- • ★ Featured star & amber highlight border
- • Top of directory search placement
- • Instant activation via claim token
📖 Detailed MCP Integration Guide
A technical breakdown of capabilities, agent workflows, and security/configuration best practices.
POST /human-loops), inspecting status (GET /human-loops/{HumanLoopName}), listing loops based on a definition (GET /human-loops#FlowDefinitionArn), and stopping loops (POST /human-loops/stop), the API offers a robust toolkit for building resilient AI systems. This is critical in enterprise use cases such as content moderation for social platforms, medical image analysis for diagnostic support, financial document processing for fraud detection, and quality control in manufacturing, where the cost of an error from a purely automated system is high and human oversight is a regulatory or quality necessity.POST /human-loops tool. It could also be tasked to "Check the current status of review loop 'job-12345' and report any errors," utilizing the GET /human-loops/{HumanLoopName} endpoint. This integration elevates the AI assistant from a mere coding helper to a collaborative operations agent, capable of bridging the gap between automated ML pipeline code and the necessary human intervention points, thereby accelerating development and debugging cycles for augmented AI applications.GET /human-loops#FlowDefinitionArn tool followed by programmatic analysis. For operational management, a command like "Immediately stop all human loops that have been in progress for over 24 hours to control costs" would involve the agent using the GET /human-loops with filtering criteria and then systematically invoking POST /human-loops/stop on the relevant items. During debugging, a developer could ask, "Retrieve the details for failed loop 'err-loop-789' and suggest code changes to the flow definition that might prevent this error," prompting the agent to fetch the loop's status and output, interpret the failure reason, and propose modifications to the underlying Lambda function or flow definition ARN configuration.a2i permissions needed (e.g., a2i:CreateHumanLoop, a2i:GetHumanLoop, a2i:ListHumanLoops, a2i:StopHumanLoop) on the specific resources (like particular flow definition ARNs) it needs to interact with, rather than broad administrative access. Configuration should also involve setting up secure credential storage, avoiding hardcoding secrets in files, and ensuring that the server's network configuration prevents unauthorized access to the credential management mechanism.Similar APIs
Other APIs in the AI & ML category.
OpenAI API
Generate text, images, and embeddings. Integrate GPT models and DALL-E into your AI agent.
API KeyAnthropic API
Access Claude AI models for text generation, analysis, and code assistance through the Anthropic API.
API KeyOpenAI API
The OpenAI API, developed and maintained by OpenAI, provides programmatic access to a suite of advanced artificial intelligence capabilities centered around large language models (LLMs). Its core functions enable developers to integrate state-of-the-art natural language processing and generation into applications. Key endpoints support text generation (completions, chat completions), content transformation (edits, classifications), semantic analysis (embeddings), and multimodal processing (audio transcriptions and translations). The API serves a broad spectrum of users, from individual developers and startups building conversational agents or content tools to large enterprises automating complex workflows, enhancing customer support, conducting sentiment analysis on large text corpora, or generating synthetic data for training. Use cases span consumer applications like intelligent writing assistants and enterprise-grade solutions for automated document summarization, code generation, and multilingual communication platforms.
Amazon CodeGuru Profiler
Amazon CodeGuru Profiler is an advanced application performance profiling service provided by Amazon Web Services (AWS). It continuously collects runtime performance data—such as CPU utilization, memory allocation, and thread contention—from live production applications, then analyzes this data using machine learning algorithms to pinpoint performance bottlenecks and inefficiencies. The API serves as the programmatic interface for managing the profiling lifecycle, allowing developers to create and configure profiling groups, adjust agent settings, retrieve performance metrics and findings, and manage notification configurations. Enterprise use cases include optimizing microservice latency in high-traffic systems, reducing cloud compute costs by identifying inefficient code paths, and maintaining application health in continuous deployment pipelines where performance regressions must be detected early. For development teams, it provides actionable insights to guide code optimization efforts based on real-world usage rather than synthetic benchmarks.
Related MCP Server Integrations
OpenAI API MCP Setup
Generate text, images, and embeddings. Integrate GPT models and DALL-E into your AI agent.
Anthropic API MCP Setup
Access Claude AI models for text generation, analysis, and code assistance through the Anthropic API.
OpenAI API MCP Setup
The OpenAI API, developed and maintained by OpenAI, provides programmatic access to a suite of advanced artificial intelligence capabilities centered around large language models (LLMs). Its core functions enable developers to integrate state-of-the-art natural language processing and generation into applications. Key endpoints support text generation (completions, chat completions), content transformation (edits, classifications), semantic analysis (embeddings), and multimodal processing (audio transcriptions and translations). The API serves a broad spectrum of users, from individual developers and startups building conversational agents or content tools to large enterprises automating complex workflows, enhancing customer support, conducting sentiment analysis on large text corpora, or generating synthetic data for training. Use cases span consumer applications like intelligent writing assistants and enterprise-grade solutions for automated document summarization, code generation, and multilingual communication platforms.
Amazon CodeGuru Profiler MCP Setup
Amazon CodeGuru Profiler is an advanced application performance profiling service provided by Amazon Web Services (AWS). It continuously collects runtime performance data—such as CPU utilization, memory allocation, and thread contention—from live production applications, then analyzes this data using machine learning algorithms to pinpoint performance bottlenecks and inefficiencies. The API serves as the programmatic interface for managing the profiling lifecycle, allowing developers to create and configure profiling groups, adjust agent settings, retrieve performance metrics and findings, and manage notification configurations. Enterprise use cases include optimizing microservice latency in high-traffic systems, reducing cloud compute costs by identifying inefficient code paths, and maintaining application health in continuous deployment pipelines where performance regressions must be detected early. For development teams, it provides actionable insights to guide code optimization efforts based on real-world usage rather than synthetic benchmarks.
Amazon CodeGuru Reviewer MCP Setup
The Amazon CodeGuru Reviewer API is a powerful programmatic interface to Amazon's automated code analysis service, designed to elevate code quality and developer productivity. This API exposes the core functionalities of a managed service that combines deep static analysis, machine learning models trained on vast code repositories, and pattern recognition to identify complex defects, security vulnerabilities, and non-idiomatic code patterns that are often missed in manual reviews. Specifically targeting Java and Python codebases, CodeGuru Reviewer analyzes code changes submitted through integrated repositories like AWS CodeCommit, GitHub, or Bitbucket, and generates actionable recommendations. Its primary enterprise use cases are integrated into continuous integration and continuous delivery (CI/CD) pipelines for automated, mandatory code quality gates; conducting security and compliance audits on critical application code; and providing scalable, consistent feedback during the pull request process, thereby reducing the burden on human reviewers and accelerating safe code deployments.