drawing-anonymizer-mcp
Related Servers
Alternatives to drawing-anonymizer-mcp
- AlicenseAqualityCmaintenanceConvert technical-drawing PDFs and engineering callouts between metric and imperial — values stamped in place, threads cross-referenced, shop-floor rounding.125MIT
- AlicenseAqualityAmaintenanceGenerates quality control plans and inspection reports from technical-drawing PDFs: tolerances, fits, threads, GD&T and surface finishes are extracted automatically by Imnoo's drawing analysis, numbered as balloons with acceptance limits and measuring instruments, and exported as a ballooned drawing PDF, an inspection package and an Excel measurement report.5MIT
Related Servers
- AlicenseAqualityAmaintenanceEnables AI agents to permanently remove personally identifiable information from PDF documents, returning redacted files with the sensitive text deleted rather than merely covered. Supports scanned documents, multiple languages, entity types, and optional human review.6217 npm1MIT
- AlicenseNot gradedqualityCmaintenanceStrips personal data and credentials from text before it reaches a model, log, or ticket, using checksum-verified detection for cards, IBANs, routing numbers, SSNs, contact details, and API keys. Placeholders such as <EMAIL_1> can later be swapped back in so the model's response is restored with the original values.2 npmMIT
- FlicenseNot gradedqualityCmaintenanceAutomatically detects and obfuscates sensitive data (PII, secrets, etc.) before Claude processes it, with lossless restoration for client deliverables.6-
- FlicenseNot gradedqualityCmaintenanceDetects whether sensitive data like emails, SSNs, and phone numbers survive in supposedly redacted PDFs, running entirely locally via WebAssembly.-
- AlicenseNot gradedqualityBmaintenanceEnables agents and applications to scan text streams for personally identifiable information, financial account numbers, JWT tokens, and cryptographic keys, returning sanitized output with deterministic zero-leakage masking. It runs as a zero-dependency MCP stdio server or importable Python module so regulatory compliance policies (GDPR/HIPAA-style) can be enforced on data before it leaves a workflow.7MIT
- AlicenseAqualityCmaintenanceProvides a local-first MCP server for multi-format document redaction, enabling detection of sensitive content, physical removal from PDFs, DOCX, XLSX, PPTX, and text files, and forensic audit with zero network calls.7AGPL 3.0
TDQS
Scored across 4 tools
Each tool occupies a distinct stage: analyze_drawing (upload+detect), load_analysis (reuse saved analysis offline), review_masking (dry-run preview), mask_drawing (write output). There is minor overlap since load_analysis and analyze_drawing both register a drawing, and mask_drawing's pdf_path one-shot path re-implements analysis, but descriptions clearly steer selection.
All four tools follow a clean verb_noun snake_case pattern: analyze_drawing, load_analysis, review_masking, mask_drawing. No mixed conventions or vague verbs, so the surface is highly predictable.
Four tools map exactly onto the anonymization lifecycle (analyze, load, review, mask), each substantial and non-redundant. This is well within the well-scoped 3-15 range with no filler.
The core detect → preview → mask pipeline plus offline reuse and share_link covers the domain well. Minor gaps like listing or deleting previously stored/registered analyses are missing, but agents can work around them within a session.