Skip to content
Original
TutorialsAWS Machine Learning BlogFrom the source· Vibhu Pareek·· 3 hours agoPicks

Discover tools at runtime with AWS Agent Registry

Who
AWS
What
explains a runtime tool discovery pattern using AWS Agent Registry
Quote
This post walks through the Discover → Instantiate → Execute loop demonstrated by the refactored Python sample.

What happened

AWS demonstrates how to use AWS Agent Registry to discover approved MCP servers and A2A agents at runtime, construct clients from their descriptors, and execute requests through a temporary inner agent. The Python sample covers order status, pricing, and returns while obtaining invocation credentials separately from discovery. The guide also explains approval workflows, search evaluation, and cases where small catalogs or fixed pipelines favor build-time wiring.

Why it matters

The sample offers a reusable pattern for discovering approved capabilities per request while keeping invocation credentials separate, with explicit guidance on when stable catalogs or fixed pipelines favor simpler wiring.

The story so far

AWS published a Python example showing how agents can use AWS Agent Registry to discover approved MCP servers and A2A agents at runtime, create clients from their descriptors, and execute requests through a temporary inner agent. The sample handles order status, pricing, and returns using a discover, instantiate, and execute loop. Only records that complete the configured approval workflow are available through the registry’s discoverable data plane. Search results do not include invocation credentials or authentication schemes, so the sample obtains invocation credentials separately. AWS also explains approval workflows and search evaluation, while noting that build-time wiring can suit small catalogs and that a deterministic flow is more straightforward when the same capabilities always run in a fixed order.

Keep reading

Latest daily · Issue 27TorchNeuron brings native PyTorch support for Hugging Face models on AWS Trainium

Trending now

  1. 1DeepSeek Open-Sources DeepInfer and Companion Components, With Model and Hardware Limits
  2. 2Mistral Releases Voxtral 3 Speech Models, Voice Agents API and LiveKit-Based SDK
  3. 3OpenAI Acquires Orchestra Bio to Support Drug Development
  4. 4Perplexity Adds Fully Local Mac Operation to Computer

Tomorrow at 08:00, a briefing like this arrives in your inbox.

The same kind of briefing as the one above: a few stories worth reading. Free. Mail starts after you confirm, and every letter has a one-click unsubscribe. Read a past issue · 2026-10-20