Get started

Documents in. Grounded data out.

DocAI parses PDFs, scans and spreadsheets into markdown, table geometry and schema-shaped JSON — with page coordinates on every segment, so an answer can point at the line it came from.

Start in four calls Browse the API

45 operations · 36 endpoints · 128 documented error codes

Parse

Upload anything, get a bundle back

Markdown in reading order, per-segment bounding boxes, table cell geometry, page renders and extracted figures. Born-digital and scanned take different paths automatically.

Extract

Your schema, filled in

Describe the fields you want and get JSON shaped to them, with citations back to the exact segment each value came from. Generate a schema from a document if you do not have one yet.

Evidence, not embeddings

Full-text search across a knowledge base returns file and segment pointers you can cite. It calls no model, so it costs no credits — search first, then read only what you need.

Work from your editor

The MCP server puts 23 DocAI tools inside Claude Code, Cursor and Codex — upload, parse, extract, split, search, and sync a local folder — without leaving the file you are in.

Code
/plugin marketplace add ProvidusAI/docai-plugins
/plugin install docai

What the tools do Install for Cursor or Codex

Cloud or your own hardware

The same API, the same tools and the same docs run against api.providus.ai or an on-prem deployment. Point DOCAI_BASE_URL at your instance; nothing else changes.

Errors you can branch on

Every failure returns a stable code beside its human-readable message. All 128 are listed, generated from the API's own registry — so the reference cannot fall behind the code.

What a document becomes

A parse produces a bundle, not a blob:

Artifact	What it is
`result_md`	The document as markdown, in reading order
`grounding_json`	Every segment with its page and bounding box
`tables_json`	Table structure with cell geometry
`result_json`	Schema-shaped extraction output
`pages`, `imgs`	Page renders and extracted figures

Because every segment carries coordinates, an answer can point at the exact place in the source it came from. That is what "grounded" means here, and it is the difference between a citation and a guess.

Where to go

Read in this order if you are new. Skip to the page you need if you are not.

Quickstart — start here: keys, the four calls that parse a document, and the conventions every endpoint shares.
Parsing — for anyone who needs the artifacts a parse produces and the coordinates that ground them.
Extraction — for pulling schema-shaped JSON, with citations, out of a parsed document.
Knowledge bases and search — for organising documents and retrieving evidence without spending credits.
Split and Classify — separate combined PDFs and label documents; document workflows covers the queued operation model they share, plus edit.
MCP server — for what each of the 23 agent tools does and what it costs.
Plugins and commands — for installing those tools into Claude Code, Cursor or Codex.
Agent guidance — for the four rules that ship with the tools, and why they are the safety mechanism.
API reference — for every endpoint, request body and response.
Error codes — for the stable code behind each failure and what to do about it.

Last modified on October 8, 2026

Quickstart

Work from your editor

The MCP server puts 23 DocAI tools inside Claude Code, Cursor and Codex — upload, parse, extract, split, search, and sync a local folder — without leaving the file you are in.

Code

/plugin marketplace add ProvidusAI/docai-plugins
/plugin install docai

What a document becomes

A parse produces a bundle, not a blob:

Artifact

What it is

result_md

The document as markdown, in reading order

grounding_json

Every segment with its page and bounding box

tables_json

Table structure with cell geometry

result_json

Schema-shaped extraction output

pages, imgs

Page renders and extracted figures

Where to go

Read in this order if you are new. Skip to the page you need if you are not.

Quickstart — start here: keys, the four calls that parse a document, and the conventions every endpoint shares.

Parsing — for anyone who needs the artifacts a parse produces and the coordinates that ground them.

Extraction — for pulling schema-shaped JSON, with citations, out of a parsed document.

Knowledge bases and search — for organising documents and retrieving evidence without spending credits.

Split and Classify — separate combined PDFs and label documents; document workflows covers the queued operation model they share, plus edit.

MCP server — for what each of the 23 agent tools does and what it costs.

Plugins and commands — for installing those tools into Claude Code, Cursor or Codex.

Agent guidance — for the four rules that ship with the tools, and why they are the safety mechanism.

API reference — for every endpoint, request body and response.

Error codes — for the stable code behind each failure and what to do about it.