# DocuPipe — MCP server on mcp.ai
> Connect your DocuPipe account and use 13 tools for document data extraction straight from your AI agent. Connect with your own API key. DocuPipe provides document parsing, structured data extraction, classification, analysis, review, workflow, and export APIs.

By: mcp.ai · official
Page: https://mcp.ai/docupipe

## Connect (MCP protocol)
Remote MCP endpoint (HTTP, streamable): https://api.mcp.ai/p_docupipe?ms=1787293560000
Add it as a custom/remote MCP connector, then authenticate when prompted.

## REST API (no MCP client required)
Every tool is also a REST endpoint, authed with a workspace API key.
Discover: GET https://api.mcp.ai/api/docupipe/_endpoints   # public; lists every endpoint
Call:     POST https://api.mcp.ai/api/docupipe/<endpoint>
  Authorization: Bearer sk_live_…   # create one at https://mcp.ai/settings/api-keys
  Content-Type: application/json
  Body: { …args }   →   { "ok": true, "tool": "<id>", "result": { … } }

## Developer docs
How to use (MCP or REST), markdown: https://mcp.ai/docupipe/skill.md
Postman collection (v2.1): https://mcp.ai/docupipe/postman.json

## Tools
- docupipe_create_schema(guidelines?: string, json_schema: object, schema_name: string) — Create a reusable extraction schema from a valid JSON Schema and optional extraction guidelines.
- docupipe_delete_document(document_id: string) — Permanently delete one previously submitted DocuPipe document by ID. This destructive operation cannot be undone.
- docupipe_delete_documents(document_ids: string[]) — Permanently delete multiple previously submitted DocuPipe documents by ID in one batch. This destructive operation cannot be undone.
- docupipe_find_documents(limit?: integer, query?: string, dataset?: string, next_cursor?: string, to_timestamp?: string, from_timestamp?: string, exclude_payload?: boolean) — Browse documents by dataset and creation time, or search filenames and document IDs when query is provided. Returns one page and a continuation cursor.
- docupipe_find_jobs(limit?: integer, job_id?: string, status?: string, end_date?: string, job_type?: string, schema_id?: string, start_date?: string, document_id?: string, next_cursor?: string, new_document_id?: string) — Retrieve one asynchronous job by ID, or list and filter jobs when job_id is omitted. Job details expose status, progress, errors, outputs, and credit use.
- docupipe_get_account_usage(include_daily_usage?: boolean) — Return current plan and credit state together with job counts and credits consumed by job type, optionally including daily usage.
- docupipe_get_document(document_id: string) — Retrieve a processed document, including processing state, parsed content, page count, metadata, and file details.
- docupipe_get_schema(schema_id: string) — Retrieve one extraction schema and its full JSON Schema definition by ID.
- docupipe_get_standardization(standardization_id: string) — Retrieve one completed standardization as structured JSON, including extraction data and field metadata.
- docupipe_list_schemas(limit?: integer, next_cursor?: string, exclude_payload?: boolean) — List extraction schemas available to the connected workspace, optionally including each full JSON Schema payload. Returns one page and an opaque continuation cursor.
- docupipe_list_standardizations(limit?: integer, schema_id?: string, document_id?: string, next_cursor?: string, exclude_payload?: boolean, standardization_ids?: string[]) — List structured extraction results, filtered by schema, document, or up to 1000 known standardization IDs. Returns one page and a continuation cursor.
- docupipe_standardize_document(pages?: integer[], timeout?: integer, schema_id?: string, guidelines?: string, document_id: string, effort_level?: string, use_metadata?: boolean) — Start V3 agentic structured extraction for one processed document and return the job and standardization IDs. Standard effort costs 2 credits per page; high effort costs 4 credits per page. Omitting s
- docupipe_upload_document(url?: string, file?: object, pages?: integer[], dataset?: string, timeout?: integer, filename?: string, metadata?: object, file_type?: string, workflow_id?: string, parse_version?: integer, file_extension?: string, processing_method?: string) — Submit one local file or remote file URL for asynchronous parsing. Returns the document and job IDs used to track processing. When workflow_id is provided, also run that existing workflow after parsin

## Example prompts
- "What can I do in DocuPipe?"
- "Show me a summary of my DocuPipe account"

## Links
Docs: https://mcp.ai/docs/mcps/docupipe
Website: https://mcp.ai/mcps/docupipe