← Back
AWS ML Blog

Agentic Resource Discovery (ARD): An open specification for agent discovery

•5 min read•
#agents#mcp#deployment
Level:Intermediate
For:AI Engineers
✦TL;DR

AWS introduces the Agent Registry, a centralized, searchable catalog for AI agents, Model Context Protocol (MCP) servers, tools, and custom resources, and announces the Agentic Resource Discovery (ARD) open specification to enable cross‑environment discovery. The registry supports cross‑account sharing within an AWS Organization, hybrid semantic‑keyword search, and flexible authorization via IAM or JWTs, while ARD standardizes resource metadata and discovery protocols across clouds, on‑prem, and SaaS. This combination lets engineers publish a resource once and have it discoverable everywhere, reducing custom integration effort.

⚡ Key Takeaways

  • Registry records capture metadata describing agents, MCP servers, tools, and custom resources.
  • The registry uses a hybrid search that blends semantic understanding with keyword matching.
  • Authorization can be configured with AWS IAM credentials or JWTs from a corporate identity provider.
  • Cross‑account sharing allows a single registry to serve an entire AWS Organization.
  • ARD defines a common metadata format and discovery protocol for multi‑environment interoperability.
💡 Why It Matters

Engineers can eliminate bespoke connectors between disparate registries, accelerating the integration of agents and tools across hybrid cloud landscapes while maintaining security and compliance controls.

✅ Practical Steps

  1. Create an AWS Agent Registry in your account, configure approval settings, and set up authorization using IAM or a JWT from your corporate IdP.
  2. Publish records for your MCP servers, agents, or tools to the registry and submit them for curator approval.
  3. Search the registry via its MCP endpoint using either natural‑language queries or exact name lookups to discover approved resources.

Want the full story? Read the original article.

Read on AWS ML Blog ↗

More like this

Introducing workload recovery and expanded infrastructure checks on Amazon SageMaker HyperPod

AWS ML Blog•#deployment

Introducing Unity Gateway Insights

Databricks Blog•#deployment

Introducing Gemini 4 Neon

Google DeepMind•#llm

DaisyRose-27B: Pushing the Frontier of Post-Training Efficiency

Hugging Face Blog•#llm

EXPLORE AI NEWS

Daily hand-picked stories on LLMs, RAG, agents and production AI — curated for engineers who ship.

BROWSE NEWS

GET THE WEEKLY DIGEST

Join engineers getting the Monday signal-over-noise AI breakdown. No spam, unsubscribe anytime.

LEARN AI ENGINEERING

Curated courses, research papers, repos and tutorials built for engineers leveling up in AI.

START LEARNING