Agentic observability with Amazon OpenSearch Service MCP Apps
Amazon OpenSearch Service now supports Model Context Protocol (MCP) Apps that extend MCP with a dual‑response pattern, returning both a concise text summary and an interactive visualization (e.g., trace waterfall, service topology) directly in the AI assistant’s chat window. This eliminates the need to switch to separate observability dashboards for verification, keeping the entire root‑cause analysis loop inside the IDE. Engineers can query OpenSearch via an agent, receive deterministic visual results rendered from the same data sources as their dashboards, and validate hypotheses instantly.
⚡ Key Takeaways
- MCP Apps generate a dual response: a text summary plus an interactive visualization rendered in‑chat.
- The visualization is produced by executing code against the same data sources that power existing OpenSearch dashboards.
- Verification time is reduced by removing the browser‑tab switching and manual re‑querying steps.
- Integration occurs through the Model Context Protocol, so agents can call the OpenSearch MCP App like any other MCP tool.
- The results are deterministic, ensuring the visual output matches the underlying query data.
By embedding live observability widgets in the agent conversation, engineers can close the verification gap, accelerating incident response cycles and maintaining a single workflow without sacrificing the accuracy of dashboard data.
✅ Practical Steps
- Configure your AI agent to call the Amazon OpenSearch Service MCP App as defined in the Model Context Protocol.
- When the agent invokes the MCP App, render the returned interactive visualization alongside the text summary in your IDE’s chat interface.
- Use the in‑chat visualizations to verify root‑cause hypotheses without opening external dashboard tabs.
Want the full story? Read the original article.
Read on AWS ML Blog ↗