DocuPipe
for LuumenAI
Parse documents, pull structured data, and check extraction results from the terminal
Connect DocuPipe and your agent can see what has been parsed, which extraction schemas exist, and what each standardization returned. Ask for the structured fields from last night's invoice batch, or check why a job is still running. When something needs to change — a new document uploaded, an extraction started, a schema created — the agent shows the plan first and waits for your approval.
The DocuPipe toolbox
13 tools: 8 read, 5 write. Reads answer instantly. Writes require approval by default. Everything is logged.
- ReadFind DocumentsBrowse documents by dataset and creation time, or search filenames and document IDs when query is provided.
- ReadFind JobsRetrieve one asynchronous job by ID, or list and filter jobs when job_id is omitted.
- ReadGet Account UsageReturn current plan and credit state together with job counts and credits consumed by job type, optionally including daily usage.
- ReadGet DocumentRetrieve a processed document, including processing state, parsed content, page count, metadata, and file details.
- ReadGet SchemaRetrieve one extraction schema and its full JSON Schema definition by ID.
- ReadGet StandardizationRetrieve one completed standardization as structured JSON, including extraction data and field metadata.
- ReadList SchemasList extraction schemas available to the connected workspace, optionally including each full JSON Schema payload.
- ReadList StandardizationsList structured extraction results, filtered by schema, document, or up to 1000 known standardization IDs.
- WriteCreate SchemaCreate a reusable extraction schema from a valid JSON Schema and optional extraction guidelines. Approval by default
- WriteDelete DocumentPermanently delete one previously submitted DocuPipe document by ID. Approval by default
- WriteDelete DocumentsPermanently delete multiple previously submitted DocuPipe documents by ID in one batch. Approval by default
- WriteStandardize DocumentStart V3 agentic structured extraction for one processed document and return the job and standardization IDs. Approval by default
- WriteUpload DocumentSubmit one local file or remote file URL for asynchronous parsing. Approval by default
One prompt, start to finish
What a governed DocuPipe run looks like inside Luumen.
Questions
Authorize once with API token. Luumen lists the scopes each action needs before you approve the connection, and credentials never appear in the chat.
Read actions answer immediately. Anything that writes — create schema, delete document, delete documents, standardize document, and more — is shown as a plan and requires approval by default, including the 2 actions classified as destructive. Administrators configure that per tool, so you decide exactly which actions can ever run unattended.
You decide. Actions are granted per agent, skill, and team, and per environment — production is not staging. Read access can be broad while writes stay narrow.
Every call to DocuPipe — read or write, approved or declined — is recorded with the actor, the input, and the result, and can be linked to the ticket or change record.
Often connected alongside
All integrations
Adobe Marketing Agent MCPAdobe Experience Platform context, sandbox switches, and async task status
AffindaRead parsed documents, collections, and annotations — change them with approval
Agent MailGive the agent its own mailbox for reading threads and sending updates
AI/ML APIInspect assistants, threads, and runs — and change them as approved stepsPut DocuPipe to work with Luumen
Connect in minutes. Every action scoped, approved, and audited from day one.