# Nanonets OCR — MCP server on mcp.ai
> Connect your Nanonets OCR account and use 6 tools for document data extraction straight from your AI agent. Connect with your own API key. Nanonets OCR extracts structured data from documents using trained, model-based OCR workflows.

By: mcp.ai · official
Page: https://mcp.ai/nanonets_ocr

## Connect (MCP protocol)
Remote MCP endpoint (HTTP, streamable): https://api.mcp.ai/p_nanonets_ocr?ms=1787293560000
Add it as a custom/remote MCP connector, then authenticate when prompted.

## REST API (no MCP client required)
Every tool is also a REST endpoint, authed with a workspace API key.
Discover: GET https://api.mcp.ai/api/nanonets_ocr/_endpoints   # public; lists every endpoint
Call:     POST https://api.mcp.ai/api/nanonets_ocr/<endpoint>
  Authorization: Bearer sk_live_…   # create one at https://mcp.ai/settings/api-keys
  Content-Type: application/json
  Body: { …args }   →   { "ok": true, "tool": "<id>", "result": { … } }

## Developer docs
How to use (MCP or REST), markdown: https://mcp.ai/nanonets_ocr/skill.md
Postman collection (v2.1): https://mcp.ai/nanonets_ocr/postman.json

## Tools
- nanonets_ocr_extract_from_url(url: string, model_id: string, request_metadata?: string) — Synchronously extract model-defined fields and tables from one publicly reachable document URL. Returns durable page and file IDs even when the model finds no matching fields.
- nanonets_ocr_get_model(model_id: string) — Get readiness, accuracy, extraction fields, and table configuration for one Nanonets OCR model.
- nanonets_ocr_get_prediction_file(model_id: string, request_file_id: string) — Get normalized extraction results for every page of one previously processed Nanonets OCR file. A successful page can have no extracted fields.
- nanonets_ocr_get_prediction_page(page_id: string, model_id: string) — Get normalized extracted fields and tables for one OCR prediction page.
- nanonets_ocr_list_models() — List the OCR models available to the connected Nanonets account, including each model's ID, readiness state, and extraction categories.
- nanonets_ocr_list_predictions(end_date: string, model_id: string, start_date: string) — List compact OCR prediction-page summaries for a model within an inclusive UTC date range. Nanonets returns the entire matching range without pagination, so prefer narrow ranges when a model has subst

## Example prompts
- "What can I do in Nanonets OCR?"
- "Show me a summary of my Nanonets OCR account"

## Links
Docs: https://mcp.ai/docs/mcps/nanonets_ocr
Website: https://mcp.ai/mcps/nanonets_ocr