monte-carlo-analyze-root-cause
Investigate data incidents and find root causes using Monte Carlo's observability data. Guides the agent through systematic investigation: alert lookup, lineage tracing, ETL checks, query analysis, and data profiling. Activates when a user asks about data issues, incidents, alerts, or why data looks wrong.
monte-carlo-data · 已有静态检查记录
安装与使用
运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。
npx skills add monte-carlo-data/mc-agent-toolkit --skill monte-carlo-analyze-root-cause技能说明
name: monte-carlo-analyze-root-cause description: | Investigate data incidents and find root causes using Monte Carlo's observability data. Guides the agent through systematic investigation: alert lookup, lineage tracing, ETL checks, query analysis, and data profiling. Activates when a user asks about data issues, incidents, alerts, or why data looks wrong. bucket: Incident Response version: 1.0.0
Monte Carlo Root Cause Analysis Skill
This skill helps investigate data incidents — freshness delays, volume anomalies, schema changes, field metric drift, and ETL failures — by guiding the agent through a systematic investigation using Monte Carlo's MCP tools. It combines observability metadata with optional direct data querying to find the root cause.
Monte Carlo tool routing (required): Always call Monte Carlo MCP tools through this plugin's bundled server, whose fully-qualified tool names are
mcp__plugin_mc-agent-toolkit_monte-carlo-mcp__<tool>(e.g.mcp__plugin_mc-agent-toolkit_monte-carlo-mcp__get_alerts). Bare tool names used in this skill (get_alerts,search,get_table, …) refer to that bundled server. If the session also has a separately-configuredmonte-carlo-mcpserver, do not route to it — it may point at a different endpoint or credentials.
Reference files live next to this skill file. Use the Read tool (not MCP resources) to access them:
- Investigation playbooks by issue type:
references/<type>-investigation.md - Data exploration patterns:
references/data-exploration.md - Intake when no incident ID:
references/intake-no-incident.md - Common root cause catalog:
references/common-root-causes.md
When to activate this skill
Activate when the user:
- Mentions a Monte Carlo alert, incident, or anomaly
- Asks "why is this table stale?" or "why did row count drop?"
- Wants to investigate a data quality issue
- Asks about freshness, volume, or schema problems
- Mentions pipeline failures (Airflow, dbt, Databricks)
- Says things like "debug this alert", "investigate this incident", "root cause analysis"
When NOT to activate this skill
Do not activate when the user is:
- Creating monitors (use the monitoring-advisor skill)
- Investigating agent-monitor alerts (agent evaluation, agent metric, agent trajectory, agent validation) or AI-agent traces/conversations (use the
monte-carlo-troubleshoot-agent-tracesskill — read../troubleshoot-agent-traces/SKILL.md) - Running impact assessments before code changes (use the prevent skill)
- Looking at storage costs (use the storage-cost-analysis skill)
- Exploring pipeline performance without a specific incident (use the performance-diagnosis skill)
Prerequisites
Required: Monte Carlo MCP server (integrations.getmontecarlo.com/mcp) must be configured and authenticated.
Optional but recommended:
- Database MCP server (Snowflake, BigQuery, Redshift, Databricks) — enables direct SQL queries for deeper data investigation. Without this, the skill can still analyze using MC's metadata tools but cannot profile actual data.
- GitHub MCP server — enables searching for recent PRs that may have caused the issue. Without this, the skill falls back to MC's query change detection.
MCP Tools Used
From Monte Carlo MCP server
| Tool | Purpose |
|---|---|
get_alerts | Fetch incident/alert details |
search | Find tables by name or keyword |
get_table | Table metadata and fields |
get_asset_lineage | Table-level upstream/downstream lineage |
get_field_lineage | Field-level lineage (trace bad data to source column) |
get_table_freshness | Table update/freshness history |
get_table_size_history | Row count and size history |
get_queries_for_table | Read/write query history |
get_query_changes | Detect SQL text modifications |
get_query_rca | Root cause analysis for failed/futile/missed queries |
get_etl_issues | ETL pipeline issues — pass platform ("airflow", "dbt", or "databricks") |
get_etl_jobs | Find ETL jobs that write to specific tables — pass platform param |
get_github_prs | Recent GitHub PRs from the account's MC GitHub integration |
get_jobs_performance | Job runtime stats, failure rates, 7-day trends |
get_change_timeline | Unified timeline: query changes + volume + ETL failures |
alert_assessment | Optional ~2-min triage of an incident — returns HIGH/MEDIUM/LOW confidence and impact. Useful when you want a quick read before deciding to escalate to TSA. |
run_troubleshooting_agent | Starts the Troubleshooting Agent (TSA) on an incident. Async by default; idempotent (returns existing results unless force_rerun=True). Auto-invoked at Step 1.5 when an incident UUID is present. |
get_troubleshooting_agent_results | Polls TSA results for an incident (status is not_found / running / success / failed). Use to check on the async run started at Step 1.5. |
Credits:
alert_assessmentandrun_troubleshooting_agentconsume Monte Carlo credits the same way the Troubleshooting Agent does when launched from the Monte Carlo UI. Each freshrun_troubleshooting_agentcall is a billable run; reuse via the built-in idempotency (don't passforce_rerun=Trueunless the user explicitly asks for a fresh analysis).
Optional external MCP tools
| Tool | Purpose |
|---|---|
| Database MCP (Snowflake, BigQuery, etc.) | Run SQL queries for data profiling |
| GitHub MCP | Search for recent PRs (alternative to MC's get_github_prs — useful if the account has no MC GitHub integration) |
Workflow
Step 1: Understand the problem (intake)
If the user provides an alert or incident ID:
- Call
get_alertswith the alert ID to fetch details. - Identify: affected table(s), issue type (freshness, volume, schema, field metric), when it started.
- Proceed to Step 2.
If the user describes a problem WITHOUT an incident ID: Read `references
阅读完整来源 ↗