AnomalyArmor Agents
AI skills and MCP server for AnomalyArmor data observability. Monitor data quality, detect schema drift, and manage alerts directly from Claude Code, Cursor, or any MCP-compatible AI tool.
Version: 0.6.0 | Tools: 52 consolidated MCP tools | Skills: 14 slash commands
Quick Start
Option 1: Claude Code Plugin (Recommended)
claude plugin marketplace add anomalyarmor/agents
claude plugin install armor@anomalyarmor
npx skills add anomalyarmor/agents
Then use skills like:
/armor:status - Check data health/armor:alerts - View and manage alerts/armor:recommend - Get AI monitoring recommendations/armor:ask - Ask questions about your data
Option 2: MCP Server
Add to your MCP configuration (Claude Code, Cursor, etc.):
{
"mcpServers": {
"armor": {
"command": "uvx",
"args": ["armor-mcp"]
}
}
}
Prerequisites
- AnomalyArmor Account: Sign up at anomalyarmor.ai
- API Key: Generate at Settings > API Keys
- Configure: Set
ARMOR_API_KEY env var or create ~/.armor/config.yaml:
api_key: aa_live_your_key_here
Available Skills
| Skill | Description | Example |
|---|
/armor:start | Guided onboarding for new users | "Help me get set up" |
/armor:status | Health summary across all assets | "Is my data healthy?" |
/armor:connect | Connect a new data source | "Connect my Snowflake warehouse" |
/armor:monitor | Set up freshness and schema monitoring | "Monitor freshness for orders table" |
/armor:alerts | Query and manage alerts | "What alerts fired yesterday?" |
/armor:ask | Natural language Q&A about your data | "What tables contain customer data?" |
/armor:analyze | Trigger AI analysis | "Analyze the finance schema" |
/armor:quality | Data quality metrics and validity rules | "Add null check for customer_id" |
/armor:coverage | Monitoring coverage analysis | "What tables have no monitoring?" |
/armor:recommend | AI-driven monitoring recommendations | "What should I monitor?" |
/armor:tags | Asset tagging and classification | "Tag this table as PII" |
/armor:investigate | Root cause analysis | "Why is this table stale?" |
/armor:lineage | Data lineage exploration | "What depends on this table?" |
/armor:profile | Table profiling and stats | "Profile the orders table" |
Tools follow a consolidated pattern: one tool per domain handles multiple operations via an action parameter, reducing context window usage while maintaining full functionality.
Health and Briefing
health_summary() - Overall data health across all assetsget_todays_briefing() - Daily AI briefing with alerts, freshness, and coverage gaps
get_alerts_summary() - Alert counts by severity and statuslist_alerts(status, severity, asset_id, from_date, to_date) - Query alerts with filterslist_inbox_alerts(status, limit) - Unresolved alerts inboxupdate_alert(alert_id, action, ...) - Acknowledge, resolve, snooze, or comment on alertsget_alert_trends(period) - Alert trends over timeget_alert_history(alert_id) - Full history for a specific alert
list_alert_rules(asset_id, is_active) - List configured rulescreate_alert_rule(asset_id, rule_type, ...) - Create new alert rulemanage_alert_rule(rule_id, action, ...) - Update, delete, enable/disable, or duplicate rules
list_assets(source, asset_type, search) - List monitored assetscreate_asset(name, source_type, connection_config) - Create data sourcemanage_asset(asset_id, action, ...) - Update, delete, test connection, or trigger discoverytrigger_asset_discovery(asset_id) - Start schema discovery
get_freshness_summary() - Freshness overview across all assetscheck_freshness(asset_id, table_path) - Check specific table freshnesssetup_freshness(asset_id, table_path, check_interval, ...) - Create freshness schedulelist_freshness_schedules(asset_id) - List configured schedulesmanage_freshness_schedule(schedule_id, action, ...) - Update, delete, pause/resume schedules
get_schema_summary() - Schema drift overviewlist_schema_changes(asset_id, severity, from_date, to_date) - List detected changescreate_schema_baseline(asset_id, description) - Create baselineenable_schema_monitoring(asset_id, schedule_type, notify_on) - Enable monitoringdisable_schema_monitoring(asset_id) - Disable monitoringget_schema_monitoring(asset_id) - View current monitoring configdry_run_schema(asset_id, schedule_type) - Test schema monitoring before enabling
get_metrics_summary(asset_id) / list_metrics(asset_id) - View metricscreate_metric(asset_id, metric_type, table_path, ...) - Create row count, null rate, or custom metricmanage_metric(metric_id, action, ...) - Update, delete, capture, or view snapshotsget_validity_summary(asset_id) / list_validity_rules(asset_id) - View validity rulescreate_validity_rule(asset_id, rule_type, table_path, ...) - Create validity rulemanage_validity_rule(rule_id, action, ...) - Update, delete, check, or view results
create_referential_check(asset_id, ...) - Create cross-table referential checkmanage_referential(check_id, action, ...) - List, delete, run, or view results
list_destinations(destination_type) - List alert destinations (Slack, email, webhook)setup_destination(destination_type, ...) - Create Slack channel, email, or webhook destinationmanage_destination(destination_id, action, ...) - Update, delete, test, enable/disablemanage_rule_destinations(rule_id, action, ...) - Link/unlink destinations to alert rules
get_coverage(asset_id) - Coverage tier and score for an assetmanage_coverage(asset_id, action) - Get next steps or apply recommended monitoringrecommend(asset_id, recommendation_type) - AI recommendations for freshness, metrics, coverage, or thresholds
ask_question(asset, question) - Natural language Q&Agenerate_intelligence(asset) - Trigger AI knowledge base generation
get_lineage(asset_id, depth, direction) - Data lineage graphjob_status(job_id) - Check async job statuscreate_tag(asset_id, name, object_path, ...) - Create and assign tagslist_tags(asset_id) / apply_tags(asset_id, ...) - List and apply tags
API Keys
get_api_key_info() - View current API key details and permissions
Examples
Check Data Health
User: Is my data healthy?
Your data health status:
- Overall: WARNING
- 3 unresolved alerts (1 critical, 2 warning)
- 2 stale tables (orders, customers)
- 1 unacknowledged schema change
- Coverage: 65% (Tier 2: Protected)
Get AI Recommendations
User: What should I monitor on my Snowflake warehouse?
Based on your table patterns and update frequency:
1. orders (high traffic) - Add freshness check (hourly), row count metric
2. customers (PII) - Enable schema drift monitoring, add null checks
3. payments (financial) - Add freshness + row count + validity rules
Want me to set these up? I can configure all three in one go.
Daily Briefing
User: What happened overnight?
Your daily briefing:
- 2 new alerts: orders table stale (6h), schema change in users
- Coverage improved: finance schema now at Tier 3 (Verified)
- Recommendation: 4 tables still have no monitoring. Run /armor:recommend.
Root Cause Analysis
User: Why is the orders table stale?
Investigation results:
- Last update: 6 hours ago (expected: hourly)
- Upstream dependency: raw_orders was last updated 8 hours ago
- Likely cause: upstream ETL job failed or delayed
- Impact: 3 downstream dashboards affected
Troubleshooting
Authentication Failed
Error: No API key configured
Solution: Set ARMOR_API_KEY environment variable or create ~/.armor/config.yaml
MCP Server Not Found
Error: MCP server 'armor' not found
Solution:
- Restart your AI tool after config changes
- Verify uvx is installed:
uvx --version
- Check MCP config syntax
Skills Not Loading
Solution:
- Verify plugin installed:
claude plugin list
- Check skills directory exists
- Restart Claude Code
Development
See AGENTS.md for development guidelines.
Support
License
MIT License - see LICENSE