菜单
Use Elastic Agent Builder and Agent Builder MCP from the IDE (define tools, test, connect Cursor/Claude)
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Debug and analyze LLM eval runs — view traces, compare runs, investigate failures, track costs. Use when debugging @kbn/evals failures, comparing eval runs, or analyzing LLM performance.
Start your security session with a personalized briefing — attacks, alerts, cases, rules, threat intel. Use as the first thing when starting security work.
Guide users from zero to a working Elastic cluster — Cloud or on-prem, connection config, first queries, and next steps.
Interactive guide for creating an APM service overview dashboard — discovers service data, presents metrics, and creates a tailored dashboard.
Interactive guide for creating SLOs from discovered APM and metric data — identifies candidates, lets user configure targets, and creates SLOs.
Create, configure, and manage Elasticsearch indices — mappings, settings, templates, data streams, and lifecycle policies.
| name | agent-builder-mcp |
| description | Use Elastic Agent Builder and Agent Builder MCP from the IDE (define tools, test, connect Cursor/Claude) |
Use this skill when the user wants to create or use custom tools with Elastic Agent Builder, or connect their IDE to Agent Builder’s MCP endpoint.
create_agent_builder_tool with name, description, and optional input_schema. The output is a tool definition to create in Agent Builder (UI or API).list_agent_builder_tools with the Agent Builder endpoint (or set AGENT_BUILDER_ENDPOINT).test_agent_builder_tool with tool name and sample arguments.get_agent_builder_mcp_config with the Agent Builder MCP URL (e.g. https://your-kibana/api/agent_builder/mcp) and transport (e.g. streamable_http). Add the returned JSON to the user’s MCP config (Cursor Settings → MCP, or Claude Code config) so the IDE uses Agent Builder’s MCP server.test_agent_builder_tool with sample input before relying on them in production.