Can Lyro send a new document to Nanonets for extraction?

No. This toolkit covers model setup, training image upload and reading results; there is no predict action that submits a fresh document. Files reach a model through your existing Nanonets upload or workflow, and Lyro reads the outcome with Get All Prediction Files and List Workflow Documents.

Do AI guidelines work on any Nanonets model?

Only on Instant Learning models. Update Model AI Guidelines sets instructions for how field and table predictions should be handled, and Nanonets limits it to that model type, so on other models the setting has nothing to apply to.

Is deleting an OCR model recoverable?

No. Delete OCR Model removes the model and all of its training data permanently. The model_id has to come from the account's model list first, so Lyro can read the model's name, type and accuracy back for confirmation before the call is made.

What can be uploaded as training material?

PNG, JPEG and PDF files through Upload Training Images by File, or a list of image URLs through Upload Training Images by URL. Both attach to a specific OCR model, and Get OCR Training Images pages through what that model already holds so the same sample is not added twice.

Nano nets MCP integration

Reports extracted field values and confidence scores, tracks workflow documents, and creates, trains and tunes OCR models.

Connect Nano nets See all integrations

11actions available

Three actions you can hand over today

Every action runs live through MCP. Nothing to build, nothing to maintain.

Get all prediction files
Lyro retrieves OCR extraction results stored in Nanonets to verify what text was successfully captured. Your team sees the parsed output and can confirm data accuracy or reprocess if needed.
Get ocr model details
Lyro pulls OCR model details including accuracy metrics and configuration. Support can verify the model is tuned correctly or recommend retraining if results degrade.
List workflow documents
Lyro lists documents processed by a workflow to track batch completions. Support verifies all expected files were parsed or identifies which ones failed.

See all 11 actions

How businesses use Nano nets + Lyro

Each card is one request a support team gets, and the Nano nets actions Lyro runs to close it.

Read back what a model extracted from a document
Lyro lists the prediction files for an OCR model and reports the extracted text, field values, confidence scores and bounding boxes, so a question about a processed invoice is answered from the result.
Get All Prediction FilesGet All ModelsGet OCR Model Details
Track documents moving through a workflow
Lyro inventories the workflows configured on the account and pages through their documents with processing status, verification status, upload time and page details, so a stuck batch is visible.
Get WorkflowsList Workflow DocumentsGet All Prediction Files
Stand up a new model for a document type
Lyro creates an OCR or image classification model with the categories it should learn, then sets the AI guidelines that govern how its field and table predictions are handled.
Create ModelGet All ModelsUpdate Model AI Guidelines
Feed a model more training material
Lyro uploads training images to a model from a local PNG, JPEG or PDF or from a list of URLs, and pages back through the samples the model already holds before adding more.
Upload Training Images by FileUpload Training Images by URLGet OCR Training Images

How it works

Get started in 3 steps

Connect once, then just ask. There is no workflow builder to learn and nothing to maintain — Lyro reads the Nano nets actions it has and picks the ones a request needs.

01
Connect Nano nets
Authorize the Nano nets account your team already uses — one consent screen, no API keys, no mapping tables. Lyro can only do what you granted that account, and you can disconnect it at any time.
02
Tell your agent what you need
Describe the job the way you would hand it to a teammate. Lyro maps it to the Nano nets actions that close it and chains as many as the request needs.
03
Watch it work
The agent runs the actions inside the conversation the customer is already in, so nobody copies data between tabs and your team can take over at any point.
Get started free

Nano nets · Lyro

Everything else about Nano nets

Setup, permissions, and the limits of what Lyro can do inside Nano nets.

No. This toolkit covers model setup, training image upload and reading results; there is no predict action that submits a fresh document. Files reach a model through your existing Nanonets upload or workflow, and Lyro reads the outcome with Get All Prediction Files and List Workflow Documents.

Every action available in Nano nets

All 11 actions your agent can call on Nano nets, straight from the live MCP connection.

Create model
Create a new image classification or OCR model.
Delete ocr model
Permanently deletes an OCR model from Nanonets.
Get all models
Retrieves all models (OCR and Image Classification) in the user's NanoNets account.
Get all prediction files
Retrieve all prediction files (OCR results) for a NanoNets model.
Get ocr model details
Retrieve details of an OCR model.
Get ocr training images
Retrieve training images for an OCR model.
Get workflows
Retrieve a list of all workflows in your Nanonets account.
List workflow documents
Retrieve a paginated list of documents processed by a NanoNets workflow.
Update model AI guidelines
Update AI Agent guidelines for an OCR model.
Upload training images by file
Upload a training image file to a specified OCR model.
Upload training images by URL
Upload training images by URL to a specified OCR model.