Agentic observability with Amazon OpenSearch Service MCP Apps
Amazon OpenSearch Service MCP Apps embed interactive observability visualizations inside AI agent chat threads
“You're not trusting the AI's interpretation. You're seeing the actual query result rendered as an interactive chart, trace waterfall, or service map.”
Amazon OpenSearch Service has launched MCP Apps, extending the Model Context Protocol with a dual-response pattern that returns both text summaries and interactive visualizations in the same AI agent chat thread. The capability targets the 'verification gap' in agentic observability — the workflow friction where engineers must leave their IDE to manually confirm agent findings in a separate browser. Visualizations are generated deterministically from actual query results rather than AI interpretation, which is a notable trust-building design choice for enterprise adoption of agentic workflows.