Agentic observability with Amazon OpenSearch Service MCP Apps
Amazon OpenSearch Service now supports MCP Apps, which return interactive visualizations alongside your AI agent's text responses. Learn how a single, locally run MCP server lets your agent move from alert to trace to logs to root cause in one conversation, and how you can verify every step inline without leaving your IDE.
Agentic observability workflows often require manual verification between the AI agent's text summary and actual dashboards. Amazon OpenSearch Service MCP Apps streamline this process by rendering relevant visualizations directly within the AI assistant's chat window. This eliminates the need for tab-switching and context switching, keeping the investigation within the same thread.
The MCP Apps capability extends the Model Context Protocol with an interactive visualization response when your AI agent calls an MCP App tool. This results in a text summary and an interactive visualization, such as a trace waterfall, service topology, or log pattern view, displayed side-by-side in the conversation. The MCP Apps architecture involves a local MCP server running on your machine, connecting to your OpenSearch UI application for authenticated queries and deterministic visualization generation.
By maintaining full control over your data and credentials, you can leverage the verification benefits of MCP Apps while keeping data within your AWS account.
Written by urgent.news from AWS Machine Learning's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
