• READY
  • MISSING
  • HUMAN
  • REPORT

How to audit deployment environments with your AI

Connect Codefresh to your agent to run instant health checks on your infrastructure. Your AI handles the scanning so you don't have to click through dashboards.

Ask AI about this page

Short answer

Can my AI check my Codefresh clusters and secrets?

Yes. Your AI uses Codefresh tools to list your delivery clusters and inspect shared contexts. This lets you confirm cluster availability and variable presence through a simple chat interface.

Audit outcomes.

Where your findings land.

What you get after the scan.

READY

Cluster readiness status

The AI identifies which Kubernetes clusters are active and available for deployments. You'll know exactly where your workloads can land.

MISSING

Variable gaps identified

Your agent flags if required shared contexts or secrets are missing. This prevents deployment failures before they happen.

HUMAN

Manual remediation needed

The AI reports what's broken but won't change your configuration. You still handle the actual fixes in the Codefresh UI.

REPORT

Environment snapshots

Get a clear summary of your current deployment landscape. Use this to verify that your staging and production environments match.

The workflow

What your AI does when the request arrives.

The AI acts as a bridge between your chat interface and your Codefresh setup.

  1. Scan clusters

    The agent pulls a full list of your active delivery clusters to check their status.

    list_delivery_clusters

  2. Check variables

    It looks through your shared contexts to see if the necessary secrets and variables exist.

    list_shared_contexts

  3. Compare state

    The AI compares the available clusters and contexts against your specific requirements.

    list_delivery_clusterslist_shared_contexts

  4. Report findings

    The agent summarizes the environment health and highlights any missing dependencies.

    list_delivery_clusters

Try it

Copy these to start.

Use these prompts to begin your audit.

Starting points

These are basic starting lines. Swap out the cluster or context names for your specific ones.

Codefresh Connector

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

Connector linkhttps://edge.vinkius.com/vk_preview_PdvyiuNy98nJgJhF2rWbswmgtQCEOaod7r7AsNCv/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 — Codefresh capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "codefresh-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_PdvyiuNy98nJgJhF2rWbswmgtQCEOaod7r7AsNCv/mcp"
    }
  }
}
Copy into chat04

  • List all my Codefresh delivery clusters and tell me which ones are active.

  • Check the shared contexts in Codefresh to see if 'prod-secrets' exists.

  • Are there any delivery clusters available that don't have access to my shared variables?

  • Audit my Codefresh environment and tell me if my deployment targets are ready.

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

Start here

Connect Codefresh once, then ask.

One connection gives your agent access to your Codefresh data. Your credentials stay encrypted and secure.

Connect Codefresh to your AI

FAQ

How the audit behaves

  • 01

    Can the AI change my cluster settings?

    No. The AI can only read data from your clusters and contexts. It cannot modify, delete, or create any resources.

  • 02

    Does the AI see my actual secret values?

    No. The AI can see that a shared context or secret exists, but it cannot read the sensitive plain-text values within them.

  • 03

    How does the AI know which clusters to check?

    It uses the list_delivery_clusters tool to see every cluster registered in your Codefresh account.

  • 04

    Can I use this with any AI client?

    Yes, as long as the client supports the Model Context Protocol (MCP).

  • 05

    What happens if a cluster is offline?

    The AI will report the status of the cluster based on the data returned from Codefresh.

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

Connect Codefresh to Claude, Cursor, ChatGPT & more