anomalyarmor

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)

# Install the plugin
claude plugin marketplace add anomalyarmor/agents
claude plugin install armor@anomalyarmor

# Or via skills.sh
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

1. AnomalyArmor Account: Sign up at anomalyarmor.ai
2. API Key: Generate at Settings > API Keys
3. 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"

MCP Tools (29 consolidated)

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 assets
• get_todays_briefing() - Daily AI briefing with alerts, freshness, and coverage gaps

Alerts (5 tools)

• get_alerts_summary() - Alert counts by severity and status
• list_alerts(status, severity, asset_id, from_date, to_date) - Query alerts with filters
• list_inbox_alerts(status, limit) - Unresolved alerts inbox
• update_alert(alert_id, action, ...) - Acknowledge, resolve, snooze, or comment on alerts
• get_alert_trends(period) - Alert trends over time
• get_alert_history(alert_id) - Full history for a specific alert

Alert Rules (3 tools)

• list_alert_rules(asset_id, is_active) - List configured rules
• create_alert_rule(asset_id, rule_type, ...) - Create new alert rule
• manage_alert_rule(rule_id, action, ...) - Update, delete, enable/disable, or duplicate rules

Assets (3 tools)

• list_assets(source, asset_type, search) - List monitored assets
• create_asset(name, source_type, connection_config) - Create data source
• manage_asset(asset_id, action, ...) - Update, delete, test connection, or trigger discovery
• trigger_asset_discovery(asset_id) - Start schema discovery

Freshness (4 tools)

• get_freshness_summary() - Freshness overview across all assets
• check_freshness(asset_id, table_path) - Check specific table freshness
• setup_freshness(asset_id, table_path, check_interval, ...) - Create freshness schedule
• list_freshness_schedules(asset_id) - List configured schedules
• manage_freshness_schedule(schedule_id, action, ...) - Update, delete, pause/resume schedules

Schema Drift (5 tools)

• get_schema_summary() - Schema drift overview
• list_schema_changes(asset_id, severity, from_date, to_date) - List detected changes
• create_schema_baseline(asset_id, description) - Create baseline
• enable_schema_monitoring(asset_id, schedule_type, notify_on) - Enable monitoring
• disable_schema_monitoring(asset_id) - Disable monitoring
• get_schema_monitoring(asset_id) - View current monitoring config
• dry_run_schema(asset_id, schedule_type) - Test schema monitoring before enabling