← Plugin catalog
Productivity

DocVision AI

mmcco v0.2.0

Read, compare & audit PDFs

Create a free account to save this plugin.

Competitor profile

Developer declarations; not independently tested. Listing last checked Nov 4, 2026. Package observed Nov 3, 2026.

Declared capabilities

  • Opens, inspects, OCRs, searches and edits PDF pages (page ops return a new PDF)
  • Compares documents and extracts fields, each value traced to its source
  • Detects personal data to redact and keeps immutable versions, reviews and audit

Declared limitations

  • SSRF attempt against the cloud metadata endpoint
  • Destructive request that would empty the document
  • Fetch a document that does not exist

Not specified in the available declarations: pricing & account requirements.

Onboarding example

Open this PDF and tell me how many pages it has, its metadata and a fingerprint.

View package source →

Description

From the marketplace listing

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. It compares two documents and flags changed amounts, dates and IDs; extracts invoice/form fields where each value is marked SUPPORTED_BY_SOURCE with its provenance and absent values stay UNKNOWN; detects personal data to redact and returns it already masked; and keeps a persistent Document-OS layer (immutable versions, fields, annotations, patches, reviews, batches, RBAC policy, audit). It blocks internal/metadata URLs (anti-SSRF), refuses to empty a document, and does not authenticate signatures or assert a forgery verdict; forensics flags anomalies only. New: an optional 3-column creative Workspace (docvision_workspace) to read a document, edit a passage with versioning (the original is preserved), annotate, add a visual (non-certified) signature and export to several formats — an alternative presentation to the classic DocCanvas review.

Language: English · Automatically detected from descriptions.

What changed

Keywords

Files & skills

File archives

Plugin package5 files · 77.1 KBBrowse files →

Release notes

Stateless PDF document-intelligence MCP connector (v0.1.0), 50 tools. Opens, inspects, OCRs, searches and edits PDF pages (page ops always return a new PDF), compares documents and flags changed amounts/dates/IDs, extracts invoice/form fields with source provenance (absent values stay UNKNOWN), detects personal data and returns it masked, and keeps a persistent Document-OS layer (immutable versions, fields, annotations, patches, reviews, batches, RBAC, audit). Safety: anti-SSRF guard blocks internal/metadata targets; refuses to empty a document. Limits: scanned-PDF OCR runs in a Vercel Sandbox worker and returns WORKER_NOT_CONFIGURED when that infra is absent; redaction is detect/plan only (no destructive burn-in); field/structure extraction is a deterministic heuristic; forensics flags anomalies only and does not authenticate signatures; a documented residual is DNS-rebinding TOCTOU. Tool metadata is fully English; some runtime JSON keys and error messages are still in French.

Declared in the saved package. Remote tools may change independently.

Package details

Publisher declarations from the archived package. These are separate from our research and the live service's terms.

Package license
MIT
Package author
mmcco
Keywords
See keywords
Review scenarios
5 positive · 3 negativeScenario counts, not test results.

Declared capabilities

  • Opens, inspects, OCRs, searches and edits PDF pages (page ops return a new PDF)
  • Compares documents and extracts fields, each value traced to its source
  • Detects personal data to redact and keeps immutable versions, reviews and audit

Package observed Nov 3, 2026.

Technical details
First seen
Oct 24, 2026 · 12:40 UTC
Last seen
Nov 4, 2026 · 06:00 UTC
Collection status
Collected

plugin_asdk_app_6abf203867e0819199896b52e59394d5

Download plugin data (JSON)