Import documents into Docparser parsers and fetch the structured data parsed from them.
Docparser ships in the w6w first-party pack. It declares 10 actions, 1 health check, and the host runs its code in a sandbox that never sees the credential.
io.w6w.docparserDocparser turns PDFs, scans and images into structured data using document parsers you configure in its app. This app lets a workflow list those parsers and their model layouts, send a document in (by public URL or as base64 content), check where it is in the import and processing pipeline, and read back the parsed results for one document or many.
It can also schedule documents for re-parsing after a parser’s rules change, or for re-integration so the parser’s configured integrations and webhooks fire again.
Built on Docparser’s v1/v2 REST API with a single secret API key. Parsers themselves are created and edited in the Docparser app; the API does not expose that.
Three routes to the same 10 actions. The Workflow tab is generated from Docparser's own manifest and carries its real ids, so it is copy-pasteable; the Code and CLI examples are the same call for any action on any app, so every app-specific value in them is a blank you fill in.
document-import-url Have Docparser fetch a publicly accessible document and queue it for parsing. Asynchronous: poll Get Document Status, then fetch the results.
document-reintegrate Schedule documents for the integration queue again, so the parser's configured integrations and webhooks fire for them.
document-reparse Schedule documents for re-parsing, e.g. after changing the parser's rules.
document-status-get Where a document is in the import and processing pipeline: in-progress flags, timestamps, page count and any failed jobs.
document-upload-content Upload a document as base64 content. Returns the new document ID and the account's remaining quota. Asynchronous: poll Get Document Status, then fetch the results.
parser-model-list List the model layouts of one document parser (id and label).
results-get Fetch the parsed data of one document. Docparser answers an array; `result` is its first element, and `items` holds all of them (more than one with Include children). Rate limit: 60 calls per minute.
results-list Fetch parsed data for a parser's documents: the last N uploaded (default 100, max 10,000), or those uploaded/processed after a date. Not paginated; narrow with the filters. Rate limit: 30 calls per minute.
A workflow step names the app and the action, and the editor fills in the
connection when you pick one. This is the Step shape from the
workflow spec, carrying Docparser's real ids.
{
"manifestVersion": "2",
"name": "docparser-example",
"steps": [
{
"id": "document-import-url",
"uses": {
"app": "io.w6w.docparser",
"action": "document-import-url",
"connection": "conn_YOUR_CONNECTION_ID"
},
"with": {
"parserId": "<parserId>",
"url": "<url>"
}
}
]
}document-import-url document-reintegrate document-reparse document-status-get document-upload-content +5 more actions available
Every app-specific value here is a blank you have to fill in. An
app action is reached through the connection that authenticates it, so the
address is a connection id, not the app id — and connections belong to your account,
so a public page cannot know yours. Create one for Docparser, then fill in
the three blanks: conn_YOUR_CONNECTION_ID, the action key, and the
parameters that action declares. The call itself is real — the shape is transcribed
from the studio's own snippet builder, which prints the same kind of blanks — but
nothing in it is specific to Docparser. The Workflow tab is where this app's
real ids are.
npm install @w6w/sdkyarn add @w6w/sdkpnpm add @w6w/sdkdeno add npm:@w6w/sdkimport { W6wClient, isActionRun } from "@w6w/sdk";
// Reads W6W_BASE_URL and W6W_TOKEN from the environment when omitted.
const client = new W6wClient();
const envelope = await client.run({
urn: "conn_YOUR_CONNECTION_ID",
action: "document-import-url",
payload: {
parserId: "<value>",
url: "<value>",
// remoteId: "<value>",
},
});
if (isActionRun(envelope)) console.log(envelope.value); npm install -g @w6w/cli w6w run conn_YOUR_CONNECTION_ID --action document-import-url --payload '{"parserId":"<value>","url":"<value>"}' Give an AI agent Docparser — without giving it Docparser's credentials. One MCP endpoint exposes every app, function and workflow the caller is entitled to, as tools it can discover and run. Access is granted per team while we onboard.
One tool call{
"name": "w6w_invoke",
"arguments": {
"ref": "app:io.w6w.docparser#document-import-url",
"input": {
"parserId": "<parserId>",
"url": "<url>"
}
}
}
Every tool names its target with a single ref. The
app: form above doesn't name a connection at all — the
host resolves which of the caller's Docparser connections to sign
with, and refuses rather than guesses when the answer is ambiguous.
The token is attached host-side, at the moment of the call. It is never a tool argument, never in the model's context, and never in a transcript — so a prompt injection has nothing to exfiltrate.
Tools are derived per end user from what that person has actually connected and is entitled to — not one shared bot identity carrying the union of everyone's access.
Multi-step work runs on the workflow engine and returns a run handle the agent can poll — retries, branching and state survive the conversation that started them.
Docparser's declared health checks are on the surface too, so an agent can tell "the vendor is down" from "your credential expired" before it burns a retry on either.
The MCP surface is part of the hosted platform. Docparser itself is MIT, and the runtime that executes it is source-available (FSL).
Docparser declares its own checks, so its health is a property of the app rather than something the host guesses at.
Status of the 'HTTP REST API' component on status.docparser.com. Other components (application, webhooks, email reception) are reported but do not decide the verdict.