
Read, compare & audit PDFs
DocVision AI is a stateless MCP document-intelligence connector for PDFs. From a file you provide (base64 or URL) it opens and inspects the document (pages, geometry, metadata, SHA-256 fingerprint), extracts the real text page by page with x/y provenance, runs OCR on scanned pages, searches, and performs page operations (rotate, delete, extract, reorder, split, merge) that always return a NEW PDF rather than modifying the original.
Example path →
https://connecteur-docvision.vercel.app/api/mcpDocVision AI — Document Intelligence platform. Layer 1 (Document Tools): open/inspect/search a PDF and REAL page operations (rotate, merge, split, extract, reorder, delete). Layer 2 (Intelligence): OCR consensus + confidence, structure, round-trip, semantic/visual diff, field extraction with provenance, redaction, forensics — deterministic, on the data provided. Layer 3 (Document OS): IMMUTABLE documents and versions, patches, fields, annotations, reviews, quality reports, audit — persistent. Rules: never complete an illegible word/number (UNKNOWN); every value traces back to its source; the original is preserved; destructive operations are previewed and confirmed. Start with .
None in the store listings or on the server