OCR Web Service provides SOAP and REST APIs for integrating Optical Character Recognition (OCR) technology into software products, mobile devices, or other web services.
OCR Web Service provides SOAP and REST APIs for integrating Optical Character Recognition (OCR) technology into software products, mobile devices, or other web services. On Nagent, OCR Web Service is exposed as a fully-configurable ai document extraction integration that any agent can call — 4 actions, and BASIC authentication. No code is required to wire OCR Web Service into your workflow — connect it once via the External Integrations panel and reuse it across every agent you build.
Agent builders use OCR Web Service to automate the kinds of tasks ai document extraction teams previously handled manually. Concrete examples — each one is a single agent step in Nagent — include:
Every action and trigger is paired with a structured input/output schema (visible in the sections below), so when you wire OCR Web Service into Helix — our agentic agent builder — the editor knows exactly what each step expects and produces. Configure once, deploy anywhere across your Nagent agents.
Every operation an agent can call against OCR Web Service, with input parameters and output schema. Drop these into any step of an agent built in Helix.
OCR_WEB_SERVICE_GET_ACCOUNT_CREDENTIALSTool to extract OCRWebService credentials (user_name, license_code) from connection metadata. Always call this before invoking OCR_WEB_SERVICE_RECOGNIZE or OCR_WEB_SERVICE_GET_ACCOUNT_INFORMATION rather than reusing cached values, as credentials may become stale. Use OCR_WEB_SERVICE_GET_ACCOUNT_INFORMATION to verify account status and quota before submitting large jobs.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
OCR_WEB_SERVICE_GET_ACCOUNT_INFORMATIONRetrieve OCRWebService account information including remaining pages, subscription plan, and expiration date. Use this tool to check your account status before large OCR jobs — exhausted page quotas will cause OCR_WEB_SERVICE_RECOGNIZE to fail mid-run. Returns details about your subscription including pages remaining and plan expiration. If credentials are invalid or stale, retrieve fresh user_name and license_code via OCR_WEB_SERVICE_GET_ACCOUNT_CREDENTIALS before retrying. Requires valid OCRWebService credentials (username and license code).
Input parameters
OCRWebService account username for authentication
OCRWebService account license code (API key) for authentication
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
OCR_WEB_SERVICE_LOGTool to retrieve OCR processing logs for a date range on your account. Invalid credentials or bad date ranges return empty data rather than an error, so an empty result may indicate incorrect inputs rather than no logs.
Input parameters
End date for log (YYYY-MM-DD)
Reserved values, if any
Start date for log (YYYY-MM-DD)
Account user name
Account license code
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
OCR_WEB_SERVICE_RECOGNIZETool to call SOAP Recognize operation. Use when performing OCR on an image to retrieve text, output document, word coordinates, and errors. Consumes page quota per call; returns HTTP 429 when limits exceeded. Check quota via OCR_WEB_SERVICE_GET_ACCOUNT_INFORMATION before large jobs; batch large PDFs in ~25–50 page chunks.
Input parameters
OCRWebService account username
OCR processing settings (languages, output, options)
OCRWebService account license code
Input file container (name + data)
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
No publicly available marketplace agent is found using this tool yet. There are 49 agents privately built on Nagent that already use OCR Web Service.
Build on Nagent
Connect OCR Web Service to any Nagent agent in minutes — no API key management, no boilerplate. Just configure and deploy.
The five questions agent builders ask before adopting a new integration.
Open the External Integrations panel inside Nagent (app.nagent.ai/externalIntegration), find OCR Web Service, and click "Connect Now." You'll authenticate with BASIC — Nagent handles credential storage and refresh automatically. Once connected, OCR Web Service is available to any agent in your workspace.
No. Nagent provides no-code integration for every tool. Once OCR Web Service is connected, you configure its 4 actions directly in the agent builder UI — no API calls, no boilerplate, no schema management.
Helix — Nagent's agentic agent builder — lets you drop OCR Web Service steps into any workflow visually. Pick an action (e.g., one of those listed above), fill in the inputs (Helix knows the required vs. optional schema for each parameter), and connect it to upstream/downstream steps. Triggers run as the entry point of an agent, so when a OCR Web Service event fires, the agent kicks off automatically.
Every OCR Web Service action and trigger ships with a fully-typed schema — input parameters with name, type, required flag, and description, plus the output payload shape. The schemas are documented in the sections above. Helix uses these schemas to validate your configuration at build time and to type-check the data flowing between steps.
Yes. While OCR Web Service ships with 4 pre-built ai document extraction actions, you can layer custom logic around them inside Helix — pre/post-processing steps, conditional branches, retries, or stitching OCR Web Service together with other connected tools. For deeper customization, talk to our team about Nagent's Agentic AI Lab — forward-deployed engineers who build OCR Web Service-based workflows tailored to your business.