canonical: https://jentic.com/apis/digiparser.com/digiparser

# DigiParser Agent API

The DigiParser API extracts structured data from documents by routing uploaded files through configured parsers and classifiers. An agent lists the parsers available to its API key, uploads files to a chosen parser or classifier, and gets back the extracted fields. A tool endpoint exposes the same actions for signed-in agent workflows.

## For AI agents

List parsers, upload documents to a parser or classifier, and extract structured data through DigiParser. Route files to the right parser and retrieve the parsed fields.

## Scope

Does not handle document storage, e-signatures, or spreadsheet generation. Use for parsing documents into structured data only.

## Capabilities

- List the parsers and classifiers available to your API key
- Upload documents to a parser to extract structured data
- Send uploads to a classifier to categorize documents
- Process a batch of files in a single upload request
- Invoke a DigiParser tool operation for an agent workflow

## Use cases

### Automated Document Extraction

An AI agent turns incoming documents into structured data: it lists the parsers available to its key, picks the one that matches the document type, and uploads the files for extraction. The agent discovers the list and upload operations through Jentic by intent, so it extracts data without hardcoding endpoint paths.

Example prompt: List the available parsers, choose the one matching the document, and upload the files to extract the structured fields

### Document Classification

A document pipeline needs to sort incoming files before processing. The agent uploads files to a classifier, which routes each document to its category so the right parser can run next. DigiParser handles the classification server-side, so the agent only submits the files.

Example prompt: Upload a batch of files to a classifier and return the category assigned to each document

### Parser Discovery

Before processing, an agent confirms which parsers its API key can use so it selects a valid one. It lists the parsers and classifiers tied to the key and matches them to the task at hand. This read-only step keeps the agent from uploading to a parser it cannot access.

Example prompt: List the parsers and classifiers available to the API key and return the one that matches a given document type

## Key endpoints

| Method | Path | Description |
| --- | --- | --- |
| GET | `/api/v1/parsers` | List parsers available to an API key |
| POST | `/api/v1/process/files` | Upload files to a parser or classifier |
| POST | `/mcp` | Call a DigiParser tool operation |

## Key resources

- **Parsers** — List the parsers and classifiers available to an API key
- **Document processing** — Upload files to a parser or classifier to extract structured data
- **Tool endpoint** — Invoke DigiParser tool operations for signed-in agent workflows

## AI readiness

This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.

- **Score:** 66 / 100
- **Maturity:** AI-Aware
- **Dimensions:**
  - Foundational Compliance: 85 / 100
  - Developer Experience & Jentic Compatibility: 65 / 100
  - AI-Readiness & Agent Experience: 47 / 100
  - Agent Usability: 94 / 100
  - Security: 70 / 100
  - AI Discoverability: 63 / 100
- **View full report:** https://jentic.com/apis/digiparser.com/digiparser/scorecard
- **How the score is calculated:** https://docs.jentic.com/reference/api-readiness-framework/overview/
- **More about the dimensions:** https://docs.jentic.com/reference/api-readiness-framework/specification/#dimensional-model-overview

### Score it yourself

Every API in the directory is allowlisted, so you can re-score it with no key required.

- **Score your own API:** https://jentic.com/scorecard.md
- **Scoring CLI agent skill:** https://github.com/jentic/jentic-api-scorecard/blob/main/skills/jentic-api-scorecard/SKILL.md

```sh
npx @jentic/api-scorecard-cli score <openapi-url>
```

## Why Jentic

- **Setup:** Wiring DigiParser by hand means issuing an API key, sending it as a bearer token in the Authorization header, and selecting the right parser before uploading files. Through Jentic you install once, import DigiParser from the API Directory, store the key once, and your agent calls it.
- **Permission scoping:** You choose which DigiParser operations your agent may call, so you can allow listing parsers and uploading documents for extraction while leaving other operations out unless you add them. That keeps the agent to the parse-and-extract path you intend.
- **Credential handling:** Your DigiParser key is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
- **Discovery method:** Agents search Jentic by intent such as list available parsers or extract data from a document, and Jentic returns the matching DigiParser operation with its input schema so the agent calls the right endpoint without reading the reference docs.

## Related APIs

- **Mindee** — Mindee extracts structured data from documents with prebuilt and custom models; DigiParser routes uploads through configurable parsers and classifiers.
- **Affinda** — Affinda is a document AI extraction platform; DigiParser offers a lighter parser-and-classifier upload flow.
- **Veryfi** — Veryfi focuses on receipts and invoices; DigiParser handles broader document types through configured parsers.

## FAQ

### What authentication does the DigiParser API use?

The DigiParser API authenticates with an API key sent as a bearer token in the Authorization header, and its spec also declares an OAuth2 authorization-code flow for signed-in agent access. Through Jentic the key is stored encrypted by your own Jentic One instance and injected at call time, so it never lands in the agent's prompt or logs.

### Can I extract structured data from documents with the DigiParser API?

Yes. List the parsers available to your key, then upload files to the parser that matches the document type and read back the extracted fields. A classifier can categorize documents first so the right parser runs.

### What are the rate limits for the DigiParser API?

The OpenAPI spec does not publish rate limits for the DigiParser API. Check DigiParser's REST API documentation for the current limits that apply to your key and plan.

### Can I limit what my agent is allowed to do with the DigiParser API?

Yes. Write a rule that allows only listing parsers and uploading documents for extraction, so the agent can parse files while other operations stay out unless you add them. Every call the agent makes is logged.

### How do I extract data from a document with the DigiParser API through Jentic?

Search Jentic for an intent like extract data from a document, store your DigiParser key once, and your agent lists the parsers and uploads the files to the matching one. To run it on your own infrastructure, install Jentic One from its GitHub repo.

### Is there a DigiParser MCP server?

Yes, DigiParser offers an MCP server. You can also connect the DigiParser REST API directly through Jentic: your agent gets the API's operations without loading another server's tool definitions into its context, your key is injected at call time by your self-hosted instance, and your rules decide which operations the agent may call.