Integration · Documents

Connect Claude & ChatGPT to DocuPipe

Ask your AI to upload an invoice to DocuPipe and pull out the fields you need, to sort a pile of files into document types, or to answer questions about a contract. It uploads, searches and reads documents, extracts data with your schemas, classifies and splits files, runs saved workflows and gives you download links for originals and Excel results.

Connect DocuPipe free

Free plan, no credit card. Takes about a minute.

Try asking

“Upload this invoice and extract it with our Invoice schema.”
The AI uploads the document from the link, starts an extraction with the schema and returns the extracted JSON when the job is done.
“What is the notice period in this contract?”
It asks the question about the document and returns the answer.
“Sort these 20 documents into our classes.”
It classifies the documents into your document classes.

What your AI can do

Upload and extract

Upload documents from a link or file, extract structured data with a schema and read or download the results.

Classify, split and ask

Classify documents into your classes, split multi-document files and ask questions across one or many documents.

Schemas and workflows

List, search and generate schemas, create classes, run saved workflows and follow jobs and reviews.

“This PDF has several documents in it. Split it.”
It splits the multi-document file into separate documents.
“Give me last week's extractions as Excel.”
It finds the extraction results and gets a temporary download link for each as an Excel file.
“How many credits have we used?”
It reads your account and workspace details, including credit usage.

82 tools for DocuPipe

These tools are switched on when you connect. You can switch any of them off, or require your approval before it runs.

ask_documentChanges dataAsk questions (`questions`) about one document (`document_id`) and get answers, with optional `instructions`.
ask_documentsChanges dataAsk questions (`questions`) across several documents (`document_ids`), a `dataset` or a schema's extracted data.
classify_documentsVisible to othersClassify documents (`document_ids`) into your classes, optionally limited to `class_ids`.
create_a_workflowVisible to othersCreate a new document. Search documents first to avoid duplicates. Has effects visible outside this system. API summary: Create a Workflow.
create_batchVisible to othersCreate a new batch. Required: document ids. Has effects visible outside this system. API summary: Standardize V2 (Legacy).
create_batch_post_review_batchVisible to othersCreate a new batch. Required: standardization ids. Has effects visible outside this system. API summary: Generate a Visual Review.
create_bulk_excelVisible to othersCreate a new bulk excel. Required: standardization ids. Has effects visible outside this system. API summary: Bulk Download Standardization Excels.
create_bulk_ocr_urlVisible to othersCreate a new bulk ocr url. Required: document ids. Has effects visible outside this system. API summary: Bulk Download OCR PDFs.
create_bulk_original_urlVisible to othersCreate a new bulk original url. Required: document ids. Has effects visible outside this system. API summary: Bulk Download Original Documents.
create_bulk_xmlVisible to othersCreate a new bulk xml. Required: standardization ids. Has effects visible outside this system. API summary: Bulk Download Standardization XMLs.
create_classChanges dataCreate a document class with `class_name` and a `description` used to recognise it.
create_classificationChanges dataCreate a new classification. Required: class id or target workspace api key. API summary: Copy a Class to Another Workspace.
create_editChanges dataCreate a new edit. Required: schema id. API summary: Edit a Schema.
create_edit_post_edit_classChanges dataCreate a new edit. Required: class id. API summary: Edit a Class.
create_generate_endpointDeletesCreate a new generate endpoint. Required: url. Destructive action; may require approval. API summary: Register an Endpoint.
create_matchingChanges dataCreate a new matching. Required: standardization id, match candidates or instructions. API summary: Match a standardization to a list of candidates.
create_merged_excelChanges dataCreate a new merged excel. Required: standardization ids. API summary: Download Merged Standardization Excel.
create_presigned_upload_urlChanges dataCreate a new document. Required: key or file extension. Search documents first to avoid duplicates. API summary: Create Presigned Upload URL.
create_projectChanges dataCreate a new project. Required: job ids. API summary: Wait For Jobs.
create_queryChanges dataCreate a new query. Required: schema id or query. API summary: Query Standardizations.
create_review_updateChanges dataCreate a new update for a review. Required: review status. API summary: Update a Review.
create_schemaChanges dataCreate a new schema. Required: schema name or json schema. Search schemas first to avoid duplicates. API summary: Add a New Schema.
create_workflow_updateChanges dataCreate a new update for a workflow. API summary: Update a Workflow.
delete_analysesMoves moneyPermanently delete a analysis. Financial or irreversible action; may require approval. API summary: Delete Multiple Analyses.
delete_classDeletesPermanently delete a class by class id. Destructive action; may require approval.
delete_documentDeletesPermanently delete a document by `document_id`. Cannot be undone.
delete_documentsMoves moneyPermanently delete a document. Financial or irreversible action; may require approval. API summary: Delete Multiple Documents.
delete_projectsMoves moneyPermanently delete a project. Financial or irreversible action; may require approval. API summary: Delete Jobs.
delete_reviewsMoves moneyPermanently delete a review. Financial or irreversible action; may require approval. API summary: Delete Reviews.
delete_schemaDeletesPermanently delete a schema by schema id. Destructive action; may require approval.
delete_standardizationDeletesPermanently delete a standardization by standardization id. Destructive action; may require approval.
delete_standardizationsMoves moneyPermanently delete a standardization. Financial or irreversible action; may require approval. API summary: Delete Multiple Standardizations.
delete_webhooks_endpointDeletesPermanently delete a webhook. Destructive action; may require approval. API summary: Deregister an Endpoint.
delete_workflowDeletesPermanently delete a workflow by workflow id. Destructive action; may require approval.
download_ocr_urlDownload the document for a ocr url. API summary: Download OCR URL.
download_public_urlDownload the document for a public url. API summary: Download Public URL.
download_standardization_pdfDownload the pdf document for a standardization. API summary: Retrieve a Standardization as PDF.
extract_document_dataChanges dataExtract structured data from a document (`document_id`) using a schema (`schema_id`). Returns a job; the result is a standardization.
generate_schemaChanges dataLet DocuPipe generate an extraction schema from example documents (`document_ids`) and `instructions`, with a `schema_name`.
get_accountGet the connected DocuPipe account and workspace details, including credit usage.
get_analysisGet the result of a question/analysis job by `analysis_id`.
get_documentGet one processed document by `document_id`, including its parsed text and status.
get_document_countList documents. Optional filters: from timestamp or to timestamp. API summary: Get Document Count.
get_document_download_linkGet a temporary download link for the original file of a document (`document_id`).
get_endpointGet one endpoint by endpoint id. API summary: Retrieve an Endpoint.
get_extractionGet the extracted JSON data of one standardization by `standardization_id`.
get_extraction_excel_linkGet a temporary download link for an extraction result as an Excel file by `standardization_id`.
get_jobGet the status of a processing job by `job_id`.
get_job_countList documents. Optional filters: include daily usage. API summary: Get Job Count.
get_reviewGet one review by `review_id`.
get_schemaGet one schema by `schema_id`, including its fields.
get_schema_countList documents. API summary: Get Schema Count.
get_standardization_countList documents. API summary: Get Standardization Count.
get_webhook_portal_linkGet one webhook. API summary: Get Webhook Portal URL.
list_analysesList analyses. Results are paginated.
list_classesList document classes (types) used for classification.
list_dataset_namesList dataset names.
list_document_proposed_schemasList proposed schemas for a document. API summary: Get Schema Proposals.
list_documentsList uploaded documents, optionally filtered by `dataset` or a time range. Paginated.
list_documents_2List documents for a document. API summary: Retrieve Detailed Processing Result.
list_endpointsList endpoints.
list_extractionsList extraction results (standardizations), filtered by `schema_id` or `document_id`.
list_extractions_2List extractions. Optional filters: extraction id, schema id, document id, extraction type or exclude payload. Results are paginated.
list_jobsList processing jobs, filtered by `status`, `job_type`, dates, `schema_id` or `document_id`.
list_review_presigned_urlsList presigned urls for a review. Optional filters: expiry hours. API summary: Generate a Presigned URL for a Review.
list_reviewsList human review tasks for extraction results.
list_reviews_2List reviews. Optional filters: review id or standardization id. API summary: Retrieve review by standardization ID.
list_schemasList extraction schemas (the field layouts DocuPipe extracts into).
list_standardization_textsList texts for a standardization. API summary: Retrieve a Standardization as Plaintext.
list_standardization_xmlsList xmls for a standardization. API summary: Retrieve a Standardization XML.
list_workflowsList your saved processing workflows.
merge_documentsVisible to othersMerge a document. Has effects visible outside this system. API summary: Merge Documents.
run_workflowChanges dataRun a saved workflow (`workflow_id`) on `inputs` (documents).
search_documentsSearch documents by text in `query`, optionally within a `dataset`.
search_extractionsSearch extraction results by text in `query`, optionally by `schema_id` or `dataset`.
search_schemasSearch schemas by name in `query`.
split_documentVisible to othersSplit a multi-document file (`document_id`) into separate documents, with optional `instructions`.
submit_schemaVisible to othersCopy a schema. Has effects visible outside this system. API summary: Copy a Schema to Another Workspace.
submit_standardizationVisible to othersMerge a standardization. Has effects visible outside this system. API summary: Merge Standardizations.
update_document_metadataChanges dataSet `metadata` (key-value pairs) on one or more documents (`document_ids`).
update_documents_datasetChanges dataUpdate an existing document. API summary: Update Dataset.
upload_documentChanges dataUpload a document for processing: pass `document` with a public `url` or a base64 `file` and its filename. Optional `dataset` and `workflow_id`. Returns the document ID.

Set up in three steps

1
Pick the app
Create a free HeyMyApps account and choose DocuPipe from the app list.
2
Paste your key
Paste your DocuPipe API key. Log in to DocuPipe and copy the API key from the dashboard. Each key belongs to one workspace.
3
Add the link to your AI
You get a personal MCP link. Add it to Claude, ChatGPT or Cursor:
1. Click your name, then Settings › Connectors › Add custom connector.
2. Paste your link as the Remote MCP server URL.
3. Switch it on from the + menu in a chat.

Questions

What can the AI do in DocuPipe?

It can upload, list, search and read documents, extract data with a schema, classify and split documents, ask questions about documents, generate schemas, create classes, run saved workflows, set metadata, delete documents and read jobs, reviews and extraction results.

Does the AI see my DocuPipe API key?

No. You paste your DocuPipe API key into HeyMyApps once. It is encrypted at rest, never shown to the AI and never shown again after you save it. The AI only sees the results of the tools you have switched on.

Can I control what the AI is allowed to do?

Yes. You choose which tools are switched on, so you can start by only reading results. Deleting a document is permanent, and it can require your approval before it runs, as can classifying and splitting. Every tool call is logged.

Does it work with ChatGPT?

Yes. In ChatGPT, open Settings › Apps & Connectors › Advanced, turn on Developer mode and add your HeyMyApps link. Developer mode needs a paid ChatGPT plan: Plus, Pro, Business or Enterprise. The same link also works in Claude (Settings › Connectors › Add custom connector), Cursor and other MCP clients.

What does it cost?

HeyMyApps has a free plan, and you do not need a credit card to start. Paid plans are billed per completed task. You connect your own DocuPipe account, so processing credits are between you and DocuPipe.

Which workspace does the AI work in?

The one your API key belongs to. Each DocuPipe API key belongs to one workspace, so use a key from the workspace you want the AI to see.