Integration · Documents
Connect Claude & ChatGPT to Nanonets OCR
Ask your AI to fetch what Nanonets extracted from a document, check which fields an OCR model reads, or classify images at public URLs. It reads extraction results per file or per page, so you can work with the data in the chat without opening Nanonets.
Free plan, no credit card. Takes about a minute.
Try asking
“Show the extracted fields for file 8c2e1 in our invoice model.”
The AI gets the extraction results for the processed file by model ID and request file ID.
“Just show me page 2 of that file.”
It gets the results for that one page by its page inference ID.
“Which fields does our receipt model extract, and is it trained?”
It reads the OCR model with its fields and training state.
What your AI can do
Extraction results
Get the extracted data for a processed file or for a single page, by model ID and the IDs returned when the file was submitted.
OCR models
Read an OCR model's fields and training state before you rely on its results.
Image classification
List your classification models and run one on images at public URLs.
“Add up the totals from these five processed invoices.”
It gets the results for each file and adds up the extracted totals in the chat.
“What classification models do we have?”
It lists your image classification models with their IDs and categories.
“Classify these three product photos with our damage model.”
It runs the classification model on the images at those public URLs and returns the predicted categories.
5 tools for Nanonets OCR
These tools are switched on when you connect. You can switch any of them off, or require your approval before it runs.
classify_image_urlsChanges dataRun an image classification model (`model_id`) on images at public `urls` and return the predicted categories.get_ocr_modelGet one OCR model by its model ID (`document_id`), including its fields and training state. Use to check a model before sending files to it.get_prediction_fileGet the extracted results for one processed file by `model_id` and `request_file_id` (returned when the file was submitted).get_prediction_pageGet the extracted results for one processed page by `model_id` and `image_level_inference_id`.list_classification_modelsList your image classification models, with their IDs and categories.
Set up in three steps
- 1
Pick the app
Create a free PipMCP account and choose Nanonets OCR from the app list.
- 2
Paste your key
Paste your Nanonets API key as the username and leave the password empty. In Nanonets open Account Info in the left panel, click API Keys and then Add a New Key, and copy the key.
- 3
Add the link to your AI
You get a personal MCP link. Add it to Claude, ChatGPT or Cursor:
- Click your name, then Settings › Connectors › Add custom connector.
- Paste your link as the Remote MCP server URL.
- Switch it on from the + menu in a chat.
Questions
What can the AI do in Nanonets OCR?
The AI can read an OCR model with its fields and training state, get extraction results for a processed file or page, list your image classification models and run a classification model on images at public URLs.
Does the AI see my Nanonets OCR API key?
No. Your Nanonets OCR API key is encrypted at rest and never shown to the AI. After you save it, it is not shown again, not even to you. The AI only sees the results of the tools it calls.
Can I control what the AI is allowed to do?
Yes. You choose which tools are switched on. Most tools only read results. The image classifier runs a model on the URLs you give it and can require your approval before it runs. Every tool call is logged.
Does it work with ChatGPT?
Yes. In ChatGPT go to Settings › Apps & Connectors › Advanced and turn on Developer mode, then add your PipMCP link. Developer mode needs a paid ChatGPT plan: Plus, Pro, Business or Enterprise. The same link also works in Claude (Settings › Connectors › Add custom connector), Cursor and other MCP clients.
What does it cost?
PipMCP has a free plan with no credit card required. Paid plans bill per completed task. You also need your own Nanonets account, and anything Nanonets charges for processing is between you and Nanonets.
Can the AI upload new documents to Nanonets?
No. The tools read results for files your models have already processed, check OCR models and classify images at public URLs. You send documents to your models the way you do today, and the AI fetches the results with the model ID and the file's request ID.
Related integrations
Let your AI work in Nanonets OCR today.
Start free. Your key stays encrypted, and you decide what the AI may do.
Connect Nanonets OCR freePipMCP is not affiliated with Nanonets OCR. Product names are trademarks of their owners.