Read image text into the fields you need
Extract text and structured fields from images.
MCP / oo CLI + Skill2 services
What You Can Do
Read photographed or scanned text and organize the fields needed for your task. A clear image and an explicit field list help produce a result that is easy to review against the source.
Read fields from an image
Present recognized text alongside the structured fields requested for review.
Recognize vehicle license plates
Read license-plate text from vehicle photos for vehicle-data workflows.
Try These Prompts
Replace the values in brackets and copy a task into your connected AI assistant.
Read fields from an image
Present recognized text alongside the structured fields requested for review.
Use OOMOL MCP with Qwen to complete this task: Use Qwen OCR to read [image URL]. Extract [field list] and show the recognized text alongside the structured values for review.
Recognize vehicle license plates
Read license-plate text from vehicle photos for vehicle-data workflows.
Use OOMOL MCP with AIsa to complete this task: Read the license plate in [image URL] and show the recognized text.
Start Working with OCR
Connect Your AI Assistant
Add OOMOL to your MCP client and sign in with your team to start using connected services.
Install oo CLI and the Skill, sign in to OOMOL, and use /oo in your AI assistant.
Install oo CLIChoose a Service
QwenChoose OOMOL-provided access when available, or connect your Qwen account.
Present recognized text alongside the structured fields requested for review.
Set up Qwen →AIsaUse OOMOL-provided access or connect your AIsa account.
Read license-plate text from vehicle photos for vehicle-data workflows.
Set up AIsa →Try Your First Task
Use OOMOL MCP with Qwen to complete this task: Read the tool definitions provided by Qwen for this OCR task. List the required inputs and supported settings so I can prepare a small example. Inspect definitions only; do not execute the task.
Services for OCR
Choose a service for your task. Tool counts show each service’s full catalog.
All Actions
Extract Text
Extract text and structured information from an image with Qwen3.5-OCR.
About 0.18 credits for 1,000 input and 1,000 output tokens; more extracted text costs more.
qwen.extract_textRecognize Carsxe License Plate
Recognize license-plate candidates in a publicly accessible HTTPS image, returning text, bounding boxes and confidence as JSON. The supplier reads the image URL.
Usage-based pricing.
aisa.recognize_carsxe_license_plateNo matching tools.
Frequently Asked Questions
What should I provide besides the image?
Name the fields you want, such as a document number, date, or table columns. Keep the original image available for reviewing uncertain text.