Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.anomalyarmor.ai/llms.txt

Use this file to discover all available pages before exploring further.

Three ways to access AnomalyArmor AI agents: Web Agent, MCP Server, and Python SDK, all sharing the same 40+ tools
AnomalyArmor gives you three ways to interact with your data platform using natural language:
Access PointWhereBest For
Web AgentBuilt into the Intelligence pageDiagnosing issues while looking at your data. No setup required.
MCP ServerClaude Code, Cursor, any MCP clientManaging observability from your IDE without switching apps.
Python SDKScripts, notebooks, CI/CDAutomating checks, building workflows, programmatic access.
All three share the same underlying tools and API. The difference is where you interact.

​
Why AI Agents?

Instead of clicking through dashboards, just ask: 
"What tables are unhealthy right now?"
"Add freshness monitoring to all gold tables"
"What changed upstream that could cause NULLs in silver_orders?"
Your AI assistant queries APIs, chains tools together, and interprets results for you.

​
Available Skills

​
Core Skills

SkillDescriptionExample
/armor:statusHealth summary”Is my data healthy?”
/armor:alertsQuery and manage alerts”What alerts fired yesterday?”
/armor:askNatural language Q&A”What tables contain PII?”
/armor:analyzeTrigger AI analysis”Analyze the finance schema”
/armor:connectConnect a data source”Connect my Snowflake warehouse”
/armor:monitorSet up monitoring”Monitor freshness for orders hourly”

​
Extended Skills

SkillDescriptionExample
/armor:qualityData quality checks”Add null check for email column”
/armor:tagsData classification”Tag this table as PII”
/armor:investigateRoot cause analysis”Why is this table stale?”
/armor:lineageData dependencies”What depends on this table?”
/armor:profileTable statistics”Profile the orders table”
/armor:coverageMonitoring coverage”What tables have no alerts?”

​
Quick Start

​
Web Agent (No Setup)

  1. Go to any asset’s Intelligence tab
  2. Click Ask Agent
  3. Start chatting

​
MCP Server (IDE)

# Claude Code (one command)
claude mcp add anomalyarmor --transport http https://mcp.anomalyarmor.ai/mcp

# Cursor (add to mcp.json)
{
  "mcpServers": {
    "anomalyarmor": {
      "url": "https://mcp.anomalyarmor.ai/mcp"
    }
  }
}
Sign in through your browser when prompted. See MCP Server setup for details.

​
Skills (Any Agent)

Install the 14 /armor:* skills into Claude Code, Cursor, Windsurf, Codex, OpenCode, or any of 40+ supported agents using the skills.sh CLI: 
npx skills add anomalyarmor/agents
Source: github.com/anomalyarmor/agents

​
Example: Morning Health Check

You: What should I prioritize this morning?

Agent: Here's your priority list:

       CRITICAL:
       - gold.fact_orders is 6 hours stale (SLA: 2h)
         Upstream staging.orders_raw is also stale.

       HIGH:
       - Schema drift: discount_pct column removed from
         gold.fact_orders on Tuesday
       - Null rate on gold.dim_customer.email spiked to 12.4%

       MEDIUM:
       - 2 validity rules failing on gold.dim_customer

       All other monitored tables are healthy.

​
Example: Investigating an Alert

You: I got a freshness alert on the orders table. What's happening?

Agent: gold.fact_orders is 6 hours overdue (SLA: 2 hours).

       I checked the upstream lineage:

         raw.events (FRESH)
           > staging.orders_raw (STALE, 8h overdue)
             > gold.fact_orders (STALE, 6h overdue)

       The issue originated in staging.orders_raw. 7 downstream
       tables are also affected:
       - gold.fact_payments
       - gold.fact_refunds
       - analytics.order_summary
       - reporting.daily_revenue
       ... and 3 more

       Recommended: Check the ETL pipeline that populates
       staging.orders_raw.

​
Example: Setting Up Monitoring

You: Set up hourly monitoring for all gold fact tables

Agent: Found 4 fact tables in the gold schema. Created freshness
       schedules:

       - gold.fact_orders: hourly, 2h SLA
       - gold.fact_payments: hourly, 2h SLA
       - gold.fact_refunds: hourly, 2h SLA
       - gold.fact_subscriptions: hourly, 2h SLA

       Want me to also add null_percentage metrics on key columns?

​
Common Questions

​
Do I need Claude to use AnomalyArmor’s AI agents?

No. The Web Agent runs in your browser with no install, and the MCP server works with any MCP-compatible client, including Cursor, Windsurf, Codex, OpenCode, and Claude Code. The /armor:* skills install into 40+ supported agents via skills.sh.

​
What’s the difference between the Web Agent, MCP server, and Python SDK?

All three call the same underlying tools. The Web Agent is built into the Intelligence page with zero setup. The MCP server lets your IDE agent manage observability without switching apps. The Python SDK is for scripts, notebooks, and CI/CD automation.

​
How do I install the /armor skills in my IDE?

Run npx skills add anomalyarmor/agents and the 14 skills install into any supported agent (Claude Code, Cursor, Windsurf, Codex, OpenCode, and more). Source is at github.com/anomalyarmor/agents.

​
Can the agent make changes to my monitoring setup, or is it read-only?

The agent can create freshness schedules, metrics, validity rules, tags, and alert rules. For any action that modifies data, it shows the plan and asks for confirmation before executing. Tool calls are always visible so you can verify what ran.

​
Does the agent have access to my actual data rows?

No. The agent queries AnomalyArmor’s metadata (schemas, freshness timestamps, monitoring results, lineage), not your row-level data. See Query Gateway for how AnomalyArmor reads customer warehouses without exfiltrating rows.

​
Next Steps

Web Agent

Chat with the agent in your browser

MCP Server

Connect your IDE

All Skills

Browse available skills

Python SDK

Programmatic access