• VISIBILITY
  • ACTION
  • DISCOVERY
  • DECISION

How to manage observability dashboards with your AI

Connect Aporia to your AI client to pull dashboard lists and run monitors through chat. You'll stop jumping between tabs to check model health.

Ask AI about this page

Short answer

How can I use AI to manage my Aporia observability?

Your AI client uses the Aporia MCP to fetch your dashboard list and trigger specific data integrity monitors. This lets you run checks and view your monitoring setup without leaving your chat interface.

The outcomes.

What you get from your AI.

The AI handles the Aporia API calls so you can focus on the results.

VISIBILITY

Dashboard inventory

The AI pulls your current dashboard list. You'll see exactly what's being tracked in your Aporia account.

ACTION

On-demand monitoring

Your agent triggers specific integrity checks. You get immediate feedback on model performance or drift.

DISCOVERY

Monitor lookup

The AI finds the right monitor for your needs. It lists your available integrity checks so you don't have to hunt for them.

DECISION

Human-led triage

The AI provides the data and the trigger. You decide if a monitor result means you need to retrain your model.

The workflow

What your AI does when you ask.

The AI translates your requests into direct Aporia actions.

  1. Fetch dashboards

    The AI retrieves your list of available observability dashboards from Aporia.

    list_dashboards

  2. Locate monitors

    It scans your account to find the specific data integrity monitors you've configured.

    list_monitors

  3. Execute checks

    The AI runs the specific monitor you requested to check for model drift or errors.

    trigger_monitor

  4. Verify status

    The AI uses the trigger tool to confirm the monitor has been initiated and provides the outcome.

    trigger_monitor

Try it

Copy these to start.

Paste these into your chat to begin.

Starting points

These are opening lines. Swap the dashboard or monitor names for your actual Aporia names.

Aporia Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_xK4X7s8PmKOy9iRpjDUr4oudy86jlYzJmpsm9w0q/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Aporia capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "aporia-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_xK4X7s8PmKOy9iRpjDUr4oudy86jlYzJmpsm9w0q/mcp"
    }
  }
}
Copy into chat04

  • Show me all my Aporia dashboards.

  • List the monitors available in my Aporia account.

  • Trigger the 'drift_check' monitor on my production dashboard.

  • Run the 'data_integrity' monitor for my LLM model.

  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Start here

Connect Aporia once, then ask.

Link your Aporia account to Vinkius. Your credentials stay encrypted, and you can start managing dashboards immediately.

Connect Aporia to your AI

FAQ

How the task behaves

  • 01

    Can the AI create a new monitor?

    No. The AI can only list existing monitors and trigger them.

  • 02

    Can the AI delete my dashboards?

    No. The AI has no tools to delete or modify your Aporia setup.

  • 03

    Can I run a monitor by name?

    Yes. Once the AI lists your monitors, you can tell it which specific one to trigger.

  • 04

    Does the AI change my dashboard settings?

    No. The AI only reads dashboard lists and triggers monitors; it cannot change your configurations.

  • 05

    What happens if a monitor fails?

    The AI will report the result of the trigger attempt. You'll need to check the Aporia UI for deep debugging.

  • More questions about Aporia? See everything the Aporia Connector can do

Connect Aporia to Claude, Cursor, ChatGPT & more