Retrieve the extraction status for a document in a sift, indicating if processing is queued, running, completed, or failed.
MIT
687,028 tools. Updated 2026-10-22 09:23
"A tool for document extraction using MinerU" matching MCP tools:
- Initiate an extraction on a document by specifying its ID and the sift to use, converting unstructured content into structured records.MIT
- Display available document folders with their extraction schemas to ensure correct filing and data extraction when uploading documents.MIT
- Convert web pages to structured Markdown while preserving tables, lists, and document hierarchy for clean content extraction.MIT
- Finalize a document upload after the presigned PUT succeeds, then dispatch extraction for a project. Requires projects:write permission.MITDestructive
- Fetch metadata for a past extraction via its log ID to get the document type, OCR provider, status, and timestamp.MIT
Matching MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to search, deep-read, and build knowledge bases from Markdown, PDF, DOCX, and PPTX documents via MCP tools for retrieval, document navigation, and ingestion.16 npm643MIT
- FlicenseNot gradedqualityDmaintenanceMCP server for parsing PDF, images, and Office documents into Markdown using MinerU, with tools for document parsing and reading previous results.-
Matching MCP Connectors
Extract attached documents with saved schemas and review owned results, confidence and validation.
AU GST/ABN receipt extraction — assigns entertainment/ITC tax codes per line, not just OCR.
- Check if the MinerU DocParse API service is running normally to confirm readiness for document conversion tasks.MIT
- Submit a document URL for async conversion to markdown. Returns a task ID to track progress. Supports PDF, DOCX, PPTX, images, and HTML.MIT
- Requeue a rejected or retryable-failed document for extraction by submitting its document ID and run ID, restoring it to pending status.MIT
- Queue a document for asynchronous entity extraction. Returns a job ID to track progress while processing runs in the background.-
- Checks the entity extraction status of a document, including job state and error details, to confirm completion before querying entities.-
- Convert PDF, DOCX, PPTX, XLSX, and images into Markdown or JSON using MinerU or PaddleOCR, with options for tables, formulas, and images.-
- Create a new SolidWorks drawing document using the default template. The new drawing becomes the active document, ready for detailing and annotation.MIT
- Extract text from images for document processing, receipt scanning, and image text extraction using OCR technology. Supports both URLs and base64 encoded images.-
- Submit a document URL for automatic classification, structured field extraction, PII masking, and quality scoring. Returns a job ID for tracking processing status.MIT
- Convert any document to markdown text with OCR for full text extraction, summarization, or translation. Provide a document ID, URL, or file data to get the complete markdown content.MIT
- Generate a browser upload link for adding a document to the workspace, returning a document_id for later extraction. Use when files can't be passed directly in chat.MIT
- Poll a Suparse extraction task by task ID to return status and document IDs, not extracted data; use those IDs to fetch or download results.MIT
- Obtain a complete list of all properties for a specified class, including system and hidden properties, to facilitate general document updates.Apache 2.0
- Upload a local document to start schema creation and generate extraction templates, returning a run ID to poll for generated template and saved document IDs.MIT
- Retrieve one page of documents and current extraction data for a Suparse task, including while processing; use cursor to paginate and refresh later.MIT