AWS bedrock-agentcore documentation change
Summary
Added a new 'Registry' service entry to the table, describing it as a centralized catalog for managing agents, MCP servers, tools, skills, and custom resources with governed workflows. Also made minor formatting changes (added leading spaces and updated apostrophe in 'Google's Gemini').
Security assessment
The change introduces a new Registry service focused on governance, publishing workflows, and resource management. While governance can have security implications, the documentation does not mention specific security features, vulnerabilities, or security incidents. The other changes are purely formatting (spacing and typography). There is no evidence of addressing a security vulnerability or weakness.
Diff
diff --git a/bedrock-agentcore/latest/devguide/what-is-bedrock-agentcore.md b/bedrock-agentcore/latest/devguide/what-is-bedrock-agentcore.md index 0bd66d141..a4e7042dd 100644 --- a//bedrock-agentcore/latest/devguide/what-is-bedrock-agentcore.md +++ b//bedrock-agentcore/latest/devguide/what-is-bedrock-agentcore.md @@ -21 +21 @@ Service | Description | Integrations -[Runtime](./agents-tools-runtime.html) | A secure, serverless runtime environment purpose-built for deploying and scaling dynamic AI agents and tools. Runtime provides fast cold starts for real-time interactions, extended runtime support for asynchronous agents, true session isolation, built-in identity, and support for multi-modal and multi-agent agentic workloads. | AgentCore Runtime works with custom frameworks and any open-source framework, including CrewAI, LangGraph, LlamaIndex, Google ADK, OpenAI Agents SDK, and Strands Agents, any foundation model in or outside of Amazon Bedrock including OpenAI, Google's Gemini, Anthropic's Claude, Amazon Nova, Meta Llama, and Mistral models, and popular protocols like MCP and A2A. +[Runtime](./agents-tools-runtime.html) | A secure, serverless runtime environment purpose-built for deploying and scaling dynamic AI agents and tools. Runtime provides fast cold starts for real-time interactions, extended runtime support for asynchronous agents, true session isolation, built-in identity, and support for multi-modal and multi-agent agentic workloads. | AgentCore Runtime works with custom frameworks and any open-source framework, including CrewAI, LangGraph, LlamaIndex, Google ADK, OpenAI Agents SDK, and Strands Agents, any foundation model in or outside of Amazon Bedrock including OpenAI, Google’s Gemini, Anthropic’s Claude, Amazon Nova, Meta Llama, and Mistral models, and popular protocols like MCP and A2A. @@ -27 +27 @@ Service | Description | Integrations -[Observability](./observability.html) | A unified view to trace, debug and monitor agent performance in production. It offers detailed visualizations of each step in the agent workflow, enabling you to inspect an agent's execution path, audit intermediate outputs, and debug performance bottlenecks and failures. | Any monitoring and observability stack that integrate with telemetry data emitted in standardized OpenTelemetry (OTEL)-compatible format +[Observability](./observability.html) | A unified view to trace, debug and monitor agent performance in production. It offers detailed visualizations of each step in the agent workflow, enabling you to inspect an agent’s execution path, audit intermediate outputs, and debug performance bottlenecks and failures. | Any monitoring and observability stack that integrate with telemetry data emitted in standardized OpenTelemetry (OTEL)-compatible format @@ -29,0 +30 @@ Service | Description | Integrations +[Registry](./registry.html) | A centralized catalog for discovering and managing agents, MCP servers, tools, skills and custom resources across your organization. Registry provides a governed workflow for publishing, reviewing, and approving resources, with hybrid semantic and keyword search so that agents and developers can find the right tools. | AgentCore Registry works with any MCP Server, Agent, Skill or Custom Resource, deployed on AWS, On-Prem or on any other Cloud environment.