Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Drawing Anonymizer

NPM · DRAWING-ANONYMIZER-MCP

Anonymize drawing PDFs: mask names, logos, addresses, emails; flattened PDF or expiring link.

+3 this week 72 Trust /100

Last scanned (18 hours ago)

Scores higher than 43% of npm servers

Category Documents and Files

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security81
  • No malware found by supply-chain analysis.Pass
  • CVE check failed: a known high-severity CVE affects pdfjs-dist 5.7.284, a direct dependency. A fixed version is available. View diagnostics → Fail
  • No install/post-install scripts declared.Pass
  • 34 of 112 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability74
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 1548 tokens (~387/item across 4 items; 4 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management53
  • Stability observed for 16 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 3 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.

  • 1 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.

  • 30 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

  • 28 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

  • 26 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

  • 24 Oct 26 +1
    • CVE-2023-54404 affects this package: high ▼ security
  • 21 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

  • 19 Oct 26 65

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 4 Nov 2026 · Analysed npm/drawing-anonymizer-mcp@0.1.0

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Vulnerabilities 2 findings
ID CVE Severity Vector Fix available
GHSA-hq66-cqwq-w95j CVE-2026-16633 high yes
GHSA-mrhx-c7xc-m3w5 CVE-2023-54404 high CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H yes

Background: What a vulnerability scan can and cannot prove →

Dependencies 112 packages
Packages resolved 112
Stale 34
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 4 exposed · ~1,081 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
analyze_drawing ~332

Upload a technical-drawing PDF to Imnoo's drawing analysis and return the sensitive data it finds — company names, logos, person names, addresses, phone numbers, emails, websites, article numbers, drawing numbers, dates and other identifying text — each with a detection id, category, value, PDF page, box (analysis image pixels), confidence, whether it sits in the title block and whether it is masked by default, plus the page sizes. Up to 4 pages are treated as one drawing. Analysis takes roughly 10–120 s; the call waits up to timeout_seconds and otherwise returns status "processing" with the drawing_id to resume with. An identical PDF analysed earlier in this session is returned from memory (no upload). analyze_drawing uploads the PDF to Imnoo's drawing analysis (the service behind the web app): 1 free analysis per day per IP address (signed-in users get more in the web app); uploaded files are deleted automatically within 24 hours and nothing else is stored. Masking itself runs locally and is unlimited.

NameTypeReqDescription
drawing_idstring–instead of pdf_path: the drawing_id of an earlier upload that returned status "processing" — keeps waiting for it without a new upload
pdf_pathstring–path to the drawing PDF (vector or scanned, ≤ 30 MB)
save_analysis_tostring–write the analysis JSON to this path (re-open it later with load_analysis, no upload needed)
timeout_secondsinteger–how long to wait for the analysis before returning "processing" (default 180)

No output schema declared.

No examples provided.

load_analysis ~138

Open a drawing analysis JSON saved earlier (analyze_drawing with save_analysis_to, or the Imnoo FileStore analysis document) and register it as a drawing for review_masking and mask_drawing. Fully offline — no upload, no daily credit. Pass pdf_path as well: masking needs the original PDF, and custom terms search its text.

NameTypeReqDescription
analysis_pathstringyespath to the analysis JSON
drawing_idstring–id to register the drawing under (default: the analysis id, else the file name)
pdf_pathstring–path to the matching drawing PDF (needed to write the masked PDF)

No output schema declared.

No examples provided.

mask_drawing ~413

Mask the drawing and write the anonymized PDF: blank (or replacement-text / own-logo) boxes over every masked detection, custom term and rectangle; by default every page is then rasterized at 288 dpi so the covered content is destroyed rather than painted over (tamper-proof single-layer PDF) and the document metadata (author, title, producer, XMP) is removed. Optional coverage report page and page selection. share_link additionally uploads the MASKED copy (never the original) and returns an expiring public link (1m, 15m, 1h or 24h). Accepts drawing_id (from analyze_drawing/load_analysis) or pdf_path for a one-shot run (analyses first). When masking is omitted for a drawing masked before in this session — including an identical PDF under another path — the previous masking is reused. Default location: next to the drawing PDF as <article number>_masked.pdf (else <file name>_masked.pdf); the source PDF is never modified.

NameTypeReqDescription
drawing_idstring–from analyze_drawing or load_analysis
maskingobject–Masking settings — shared by review_masking and mask_drawing; pass the same object to both so the PDF matches the reviewed masks. Everything is optional; the defaults reproduce the web app.
output_pathstring–target .pdf path, or a directory (default: next to the drawing PDF, else the working directory)
overwriteboolean–allow replacing an existing output file
pdf_pathstring–the drawing PDF — analysed first when it is not known yet (one daily credit), or the original PDF for a drawing_id loaded without one
share_linkstring–also create an expiring public link to the masked copy, valid for 1 minute, 15 minutes, 1 hour or 24 hours
timeout_secondsinteger–with pdf_path: how long to wait for the analysis (default 180)

No output schema declared.

No examples provided.

review_masking ~198

Compose the masks for an analysed drawing exactly as mask_drawing will, without writing anything: which detections are masked (with their replacement in mode "replace") and which stay visible, custom-term matches, rectangles, the article-number stamp, the pages written, the anonymity score (0–100) with its warnings, the output file name, and visible_text_after_masking — the text a reader will still see on each page (from the PDF text layer). Use it to find leftovers (a customer name in the notes, a person the analysis missed) and add them as terms or rectangles. Deterministic and offline — iterate freely.

NameTypeReqDescription
drawing_idstringyesfrom analyze_drawing or load_analysis
maskingobject–Masking settings — shared by review_masking and mask_drawing; pass the same object to both so the PDF matches the reviewed masks. Everything is optional; the defaults reproduce the web app.

No output schema declared.

No examples provided.

Install

How do I install the Drawing Anonymizer MCP server?

Drawing Anonymizer runs locally as an npm package, launched with npx -y drawing-anonymizer-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · drawing-anonymizer-mcp

# add to Claude Code
claude mcp add com-imnoo-drawing-anonymizer -- npx -y drawing-anonymizer-mcp
Common questions

What is the Drawing Anonymizer MCP server?

Drawing Anonymizer is an MCP server listed in the public MCP registry as com.imnoo/drawing-anonymizer. Anonymize drawing PDFs: mask names, logos, addresses, emails; flattened PDF or expiring link. This page covers its npm package (drawing-anonymizer-mcp).

Is the Drawing Anonymizer MCP server safe to use?

Drawing Anonymizer scores 72 out of 100 on VerifyMCP. We recorded 2 known advisories against it as of 4 November 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Drawing Anonymizer MCP server expose?

Drawing Anonymizer exposes 4 tools: analyze_drawing, load_analysis, review_masking, mask_drawing. Their descriptions and schemas cost roughly 1,081 tokens of context every time the server is loaded.

Is the Drawing Anonymizer MCP server still maintained?

Drawing Anonymizer is still listed as active in the MCP registry. We last reached this channel on 4 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the Drawing Anonymizer MCP server under?

Drawing Anonymizer declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.