• MISSING
  • VALID
  • HUMAN
  • SUMMARY

How to audit content schemas with your AI

Connect Kontent.ai to your agent to run automated checks on your content models. It scans your repository to ensure every content type follows your required metadata rules.

Ask AI about this page

Short answer

Can my AI check if my Kontent.ai content types have the right metadata?

Yes. Your agent uses the Kontent.ai MCP to pull your content type definitions and check them against your specific requirements. You'll get a clear list of which models are missing required fields or metadata.

Where every issue lands.

Audit outcomes

The AI processes your schema definitions and organizes the results into these categories.

MISSING

Required field gaps

The agent identifies content types that lack mandatory metadata. You get a list of exactly which fields are missing.

VALID

Compliant schemas

The AI confirms which content types meet all your specified metadata requirements. These are ready for production.

HUMAN

Manual review needed

If a schema is partially correct but has naming inconsistencies, the agent flags it for you to check manually.

SUMMARY

Repository health

The agent provides a high-level view of how many content types pass or fail your audit. This helps you see the scale of the cleanup.

The workflow

What your AI does when the audit starts.

The agent moves through your Kontent.ai repository to map out your structure before checking for errors.

  1. Map the repository

    The agent pulls a full list of every content type currently active in your Kontent.ai environment.

    list_content_types

  2. Fetch schema details

    The agent selects specific content types to examine their internal structure and field settings.

    get_content_type

  3. Inspect individual fields

    The agent looks deep into each element to check for specific metadata properties or required flags.

    get_content_type_element

  4. Compare and report

    The agent compares the gathered data against your instructions and highlights any discrepancies.

    get_content_type

Try it

Copy these to start.

Use these prompts to kick off your audit.

Starting points

Swap out the bracketed text for your actual content type names or specific field requirements.

Kontent.ai Connector

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

Connector linkhttps://edge.vinkius.com/vk_preview_RHPKSkjWKzcGtG2RsrCEiLCsL40xpag39Ae5gsji/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 — Kontent.ai capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "kontentai-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_RHPKSkjWKzcGtG2RsrCEiLCsL40xpag39Ae5gsji/mcp"
    }
  }
}
Copy into chat04

  • List all content types in my Kontent.ai repository and tell me which ones are missing a 'description' field.

  • Check the 'Article' content type and verify if the 'author' element is marked as required.

  • Audit my Kontent.ai schema to ensure every content type has a 'meta_title' element.

  • Find all content types that do not have a 'last_updated' metadata field.

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

Start here

Connect Kontent.ai once, then ask.

One click connects your agent to your Kontent.ai account. Your credentials stay encrypted and secure, and you can start auditing immediately.

Connect Kontent.ai to your AI

FAQ

How the audit works

  • 01

    Can the AI change my content types?

    No. The agent can only read your schema definitions. It cannot create, delete, or modify any content types or elements in Kontent.ai.

  • 02

    Does the AI see my actual content entries?

    No. This specific task only looks at the content type definitions (the schemas), not the individual pieces of content you have published.

  • 03

    How does the AI know what fields are 'required'?

    The agent reads the configuration of each element within the content type to see if the required flag is set to true.

  • 04

    Can I audit specific content types only?

    Yes. You can tell your agent to focus on a single content type or a specific subset of your repository.

  • 05

    What happens if a field name is slightly different?

    The agent will flag it as missing if the name doesn't match your prompt exactly. You'll need to review these cases manually.

  • More questions about Kontent.ai? See everything the Kontent.ai Connector can do

Connect Kontent.ai to Claude, Cursor, ChatGPT & more