• CAPACITY
  • LIMITS
  • BOTTLENECKS
  • HUMAN

How to audit compute resources with your AI

Connect your Azure Synapse Analytics environment once. From there, your AI scans your pool configurations to find capacity gaps.

Ask AI about this page

Short answer

How can I audit my Synapse compute resources with AI?

Your AI pulls the current configuration and capacity for your SQL and Spark pools. You'll get a clear view of your provisioning limits and actual usage. Here is how it works.

Audit outcomes

Where your audit data lands.

The AI organizes the raw pool data into these specific outcomes.

CAPACITY

Usage snapshots

The AI compares your current pool settings against your limits. You get a direct view of available headroom.

LIMITS

Provisioning checks

The AI identifies where your SQL or Spark pools are hitting hard constraints. This highlights where you might need to scale.

BOTTLENECKS

Resource gaps

The AI flags pools that are over-provisioned or running too close to their ceiling. You get a list of specific targets for optimization.

HUMAN

Manual adjustments

The AI only reads and reports. You still handle the actual scaling or resizing of pools within the Azure portal.

The workflow

What your AI does when the audit request arrives.

The AI acts as a bridge between your chat interface and your Synapse environment.

  1. Scan SQL pools

    The AI pulls the configuration and capacity details for every SQL pool in your workspace.

    list_sql_pools

  2. Scan Spark pools

    The AI gathers the same provisioning and capacity data for your Spark pools.

    list_spark_pools

  3. Analyze limits

    The AI compares the gathered data to find where you are hitting provisioning ceilings.

    list_sql_poolslist_spark_pools

  4. Report findings

    The AI presents a summary of which pools are healthy and which ones are nearing capacity.

    list_sql_poolslist_spark_pools

Try it

Copy these to start.

Use these prompts to kick off your audit.

Starting points

These are just starting points. You can swap out the pool names or specific resource types to get more targeted answers.

Azure Synapse Analytics Connector

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

Connector linkhttps://edge.vinkius.com/vk_preview_MqO0WqrVDGRBLkpjn3kMhJJjBY9bjnhtsMU5bx9E/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 — Azure Synapse Analytics capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "azure-synapse-analytics-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_MqO0WqrVDGRBLkpjn3kMhJJjBY9bjnhtsMU5bx9E/mcp"
    }
  }
}
Copy into chat04

  • List all my SQL pools and tell me if any are hitting their provisioning limits.

  • Check my Spark pools and show me the current capacity for each.

  • Which of my Synapse compute resources are currently over-provisioned?

  • Compare the capacity of my production SQL pool against its configured limits.

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

Start here

Connect Azure Synapse Analytics once, then ask.

You only need to link your account once. Your credentials stay encrypted, and you can immediately start asking questions about your pools.

Connect Azure Synapse Analytics to your AI

FAQ

How this task behaves.

  • 01

    Can the AI resize my SQL pools automatically?

    No. The AI can only read and report on your current configurations. You must perform any scaling or resizing manually in Azure.

  • 02

    Does the AI see my actual data inside the tables?

    No. The AI only accesses the metadata and configuration settings for your SQL and Spark pools.

  • 03

    Can I audit specific Spark pools instead of all of them?

    Yes. You can ask the AI to focus on a specific pool by name.

  • 04

    Will this tool delete any of my compute resources?

    No. This MCP only has read-only capabilities for listing pools. It cannot delete or modify anything.

  • 05

    How does the AI know if a pool is at capacity?

    The AI uses the capacity and provisioning data retrieved from your pools to calculate how much headroom remains.

  • More questions about Azure Synapse Analytics? The Connector page answers them. See everything the Azure Synapse Analytics Connector can do

Connect Azure Synapse Analytics to Claude, Cursor, ChatGPT & more