이 페이지는 AI로 자동 번역되었습니다. 기술적인 세부 사항은 원문을 확인하세요. 원문 보기
An MCP App that brings interactive SRE workflows for Elastic Observability directly into Claude, VS Code, and other MCP-compatible AI hosts.
개요
An MCP App that brings interactive SRE workflows for Elastic Observability directly into Claude, VS Code, and other MCP-compatible AI hosts. Built on the Model Context Protocol with interactive UI extensions that render inline in the conversation. MCP Apps extend the Model Context Protocol to let tool servers return interactive HTML interfaces — dashboards, forms, visualizations — that render inside the AI conversation. The LLM calls a tool, and instead of just returning text, an interactive UI appears alongside the response. This project is an experimental reference implementation published for exploration and feedback. It is not covered by Elastic support SLAs, may change or break without notice, and is not intended for production use. File issues on GitHub; responses are best-effort. This project provides six interactive SRE tools, each with a rich React-based UI that renders inline when Claude (or another MCP host) calls the tool.
README
원문 README의 일부입니다. 원문 보기.
Elastic Observability MCP App
An MCP App that brings interactive SRE workflows for Elastic Observability directly into Claude, VS Code, and other MCP-compatible AI hosts. Built on the Model Context Protocol with interactive UI extensions that render inline in the conversation.
What are MCP Apps? MCP Apps extend the Model Context Protocol to let tool servers return interactive HTML interfaces — dashboards, forms, visualizations — that render inside the AI conversation. The LLM calls a tool, and instead of just returning text, an interactive UI appears alongside the response.
[!WARNING] Technical preview — not officially supported. This project is an experimental reference implementation published for exploration and feedback. It is not covered by Elastic support SLAs, may change or break without notice, and is not intended for production use. File issues on GitHub; responses are best-effort.
What This Does
This project provides six interactive SRE tools, each with a rich React-based UI that renders inline when Claude (or another MCP host) calls the tool. The Dependency column shows what each tool needs from your deployment — Universal tools work on any Elastic Observability cluster; the others require APM, ML, or Kubernetes telemetry.
| Tool | Dependency | What It Does |
|---|---|---|
| observe | Universal | Transient ES|QL + ML-anomaly access primitive. Modes: now (single read), table (full result with auto-chart for time-series shapes), metric (live-sample or block until a threshold), anomaly (block until an ML anomaly fires). |
| manage-alerts | Universal (needs Kibana) | Create, list, get, and delete Kibana custom-threshold alerting rules. Filter the list by source (MCP-created vs all), paginate, and inspect rule details inline. Omit the Kibana URL to run read-only. |
| ml-anomalies | ML jobs | Query ML anomaly records and open an inline anomaly explainer with overview list + drill-into-detail flow, byte/ms/pct unit inference on Actual / Typical, and an annotated time-series chart of actual vs learned-typical. |
설치
This server does not publish a one-line install command.
Open the repository installation guide MCP 초보자라면? mcpskill.org 가이드부터 시작하세요 →