- SCHEMA
- PROPERTIES
- INVENTORY
- HUMAN
Short answer
Can my AI check my TOSCA blueprints for errors?
Yes. Your AI uses Cloudify tools to pull blueprint data and compare it against your required schemas or property sets. You'll get a clear breakdown of where your orchestration logic fails or deviates from your standards.
Audit outcomes
Where your data lands
What happens when your AI scans your blueprints.
SCHEMA
Validation reports
The AI compares TOSCA structures against your expected models. You get a list of blueprints that don't match your required orchestration logic.
PROPERTIES
Property drift detection
Your agent checks specific property values across your manager. It flags any blueprints where configuration values have drifted from your defined standards.
INVENTORY
Blueprint cataloging
The AI maps out every blueprint currently in your manager. This gives you a clean overview of your entire orchestration landscape.
HUMAN
Manual fixes
The AI identifies the errors but doesn't change your code. You decide which blueprints need manual updates or re-orchestration.
The workflow
What your AI does when the audit starts.
The AI handles the heavy lifting of data retrieval and comparison.
Cataloging
Your agent first gathers a complete list of all available blueprints in your environment.
list_blueprintsData extraction
The AI pulls the specific TOSCA data and property sets for the blueprints you want to inspect.
get_blueprintSchema comparison
Your agent compares the extracted data against your target orchestration schema to find mismatches.
get_blueprintError reporting
The AI summarizes every property error or structural flaw it found during the scan.
list_blueprintsget_blueprint
Try it
Copy these to start.
Use these prompts to begin your audit.
Starting points
These are ideas to get you moving. Swap out the blueprint names for your actual ones.
Cloudify Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_YIdeRn0hAqBloQdQ3tH0JMinN2MrEDBkMrsxMQwv/mcpClaude Desktop
Follow the steps below to connect in seconds.
- 1In Claude Desktop, open Settings → Connectors.
- 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
- 3Click Add and start a new chat — Cloudify capabilities are ready to use.
{
"mcpServers": {
"cloudify-mcp": {
"url": "https://edge.vinkius.com/vk_preview_YIdeRn0hAqBloQdQ3tH0JMinN2MrEDBkMrsxMQwv/mcp"
}
}
}List all my blueprints and tell me how many are currently active.
Get the data for the 'web-server-v2' blueprint and check if the properties match my standard schema.
Scan all blueprints and find any that are missing the 'network_id' property.
Compare the 'database-cluster' blueprint against the requirements I just pasted here.
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Start here
Connect Cloudify once, then ask.
Just enter your credentials once. Your connection is encrypted, and you can immediately start asking your AI about your blueprints.
Connect Cloudify to your AIFAQ
How this task behaves
- 01
Can the AI fix my broken blueprints?
No. The AI can only read and inspect blueprint data. You must perform all edits and deployments yourself.
- 02
Can the AI delete blueprints from my manager?
No. This MCP only provides tools to list and get blueprint data. It cannot delete or modify anything in Cloudify.
- 03
How does the AI know what a 'correct' blueprint looks like?
You provide the standard. You tell the AI what the schema or property requirements should be, and it compares the blueprint data to your instructions.
- 04
Does this work with any TOSCA-compliant manager?
No. This MCP is built specifically for Cloudify.
- 05
Can I audit blueprints one by one?
Yes. You can ask the AI to look at a single specific blueprint by name.
More questions about Cloudify? The Connector page answers them. See everything the Cloudify Connector can do
Connect Cloudify to Claude, Cursor, ChatGPT & more
