- RAW
- RUNNING
- STRUCTURED
- HUMAN
Short answer
How can I use my AI to extract data from files?
You upload a file to the AirOps MCP, which triggers a specific workflow to parse the content into a structured format. Your AI then receives the processed results to use in your conversation. This breakdown shows how the tools handle the handoff.
Data outcomes
Where your data ends up.
The extraction process moves data from raw files to usable formats through these four outcomes.
RAW
Uploaded files
The process starts when you provide a file. The AI sends this file to AirOps to begin the extraction.
RUNNING
Active workflows
AirOps runs your specific extraction logic. Your AI monitors the progress until the data is ready.
STRUCTURED
Cleaned data
The final output is organized data that your AI can read, filter, or summarize immediately.
HUMAN
Manual review
You decide if the extracted data is accurate. The AI provides the results, but you keep final control.
The workflow
What your AI does when the file arrives.
The AI acts as the bridge between your local files and the AirOps execution engine.
Upload the file
Your AI sends the document or image you want to process to the AirOps environment.
upload_fileTrigger extraction
The AI starts the specific AirOps workflow designed to parse your data.
execute_workflow_syncMonitor progress
If the extraction takes time, the AI checks the status of the job until it finishes.
get_execution_statusHandle large jobs
For massive datasets, the AI can trigger a background process and move on to other tasks.
execute_workflow_async
Try it
Copy these to start.
Use these prompts to kick off your first extraction task.
Starting points
Swap the bracketed text for your actual file names or specific workflow IDs.
AirOps Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_0guLp9ho3nBBv2oVWQwh3EyBDOaKJy251N5l5oxu/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 — AirOps capabilities are ready to use.
{
"mcpServers": {
"airops-mcp": {
"url": "https://edge.vinkius.com/vk_preview_0guLp9ho3nBBv2oVWQwh3EyBDOaKJy251N5l5oxu/mcp"
}
}
}Extract the invoice details from this PDF: [invoice_001.pdf]
Run the data cleaning workflow for this CSV: [customer_list.csv]
Use the AirOps extraction workflow on this image: [receipt_photo.jpg]
Check the status of my last data extraction job.
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Start here
Connect AirOps once, then ask.
One click connects the MCP to your client. Your credentials stay encrypted and secure on our side.
Connect AirOps to your AIFAQ
How the extraction behaves
- 01
Can the AI change my AirOps workflow settings?
No. The AI can only trigger existing workflows. It cannot modify the logic or configuration within AirOps.
- 02
Does the AI delete my uploaded files?
No. The AI only uploads files to trigger the process. It does not have the capability to delete files from AirOps.
- 03
Can I run multiple extractions at once?
Yes. You can trigger multiple workflows, including asynchronous ones, to handle several files in sequence or parallel.
- 04
What happens if the extraction fails?
The AI will receive a status update indicating the failure. You can then decide whether to retry or fix the input file.
- 05
Do I need to manually format the data?
No. The AirOps workflow handles the formatting based on how you built the workflow. The AI just receives the result.
More questions about AirOps? See everything the AirOps Connector can do
Connect AirOps to Claude, Cursor, ChatGPT & more
