anonymize-mcp

v0.10.0 suspicious
4.0
Medium Risk

MCP server wrapping LINDAT NLP tools — production-grade anonymization, multilingual NER (33+ languages), UDPipe (961 models), Charles Translator (8 languages), PONK readability, Korektor spellcheck. Non-commercial use only.

🤖 AI Analysis

Final verdict: SUSPICIOUS

The package is assessed as suspicious due to its moderate metadata risk and network risk, despite no immediate signs of shell risk or direct malicious activities.

  • Low repository activity and sparse maintainer information
  • Downloads a model file from an external URL
Per-check LLM notes
  • Network: The package appears to be downloading a model file from a URL, which is common for machine learning packages but should be reviewed for the legitimacy of the source.
  • Shell: No shell execution patterns were detected.
  • Metadata: The repository's low activity and the maintainer's sparse information raise concerns about potential malicious intent.

📦 Package Quality Overall: Medium (5.0/10)

◈ Medium Test Suite 6.0

Partial test coverage signals detected

  • Test runner config found: pyproject.toml
◈ Medium Documentation 5.0

Some documentation present

  • Detailed PyPI description (12339 chars)
○ Low Contributing Guide 4.0

No contributing guide or governance files found

  • Development Status classifier >= Beta
◈ Medium Type Annotations 5.0

Partial type annotation coverage

  • 94 type-annotated function signatures detected in source
◈ Medium Multiple Contributors 5.0

Limited contributor diversity

  • 1 unique contributor(s) across 96 commits in Buggy1111/anonymize-mcp
  • Single author but highly active (96 commits)

🔬 Heuristic Checks

⚠ Outbound Network Calls score 3.0

Found 2 network call pattern(s)

  • flush=True) try: urllib.request.urlretrieve(_MODEL_ZIP_URL, zip_path, reporthook=_progress)
  • try: async with httpx.AsyncClient(timeout=timeout, follow_redirects=True) as client:
✓ Code Obfuscation

No obfuscation patterns detected

✓ Shell / Subprocess Execution

No shell execution patterns detected

✓ Credential Harvesting

No credential harvesting patterns detected

✓ Typosquatting

No typosquatting candidates detected

✓ Registered Email Domain

Email domain looks legitimate: gmail.com>

✓ Suspicious Page Links

All external links appear legitimate

⚠ Git Repository History score 2.5

Git history flags: Repository has zero stars and zero forks

  • Repository has zero stars and zero forks
⚠ Maintainer History score 4.0

2 maintainer concern(s) found

  • Author name is missing or very short
  • Author "" appears to have only 1 package on PyPI (new or inactive account)
✓ Known CVE Vulnerabilities

No known vulnerabilities found in OSV database.

💡 AI App Starter Prompt

Use this prompt to build a project with anonymize-mcp 
Create a multilingual document anonymizer and information extractor tool using the Python package 'anonymize-mcp'. This tool will serve as a command-line interface (CLI) application allowing users to upload text files in various languages, and receive back anonymized versions of these documents along with extracted named entities (NER). Additionally, the application should provide options for checking the readability of the anonymized text and suggesting corrections for spelling errors. Here’s a detailed breakdown of the project steps and features:

1. **Setup**: Install 'anonymize-mcp' and any other necessary dependencies.
2. **User Input Handling**: Develop functionality to accept text file inputs from users in different languages.
3. **Anonymization Process**: Use 'anonymize-mcp' to anonymize personal data within the uploaded texts while preserving the overall context.
4. **Named Entity Recognition (NER)**: Utilize the multilingual NER capabilities of 'anonymize-mcp' to identify and classify named entities such as persons, organizations, locations, etc.
5. **Readability Check**: Integrate PONK from 'anonymize-mcp' to assess the readability of the anonymized texts.
6. **Spelling Correction**: Implement Korektor from 'anonymize-mcp' to correct any misspelled words in the anonymized text.
7. **Output Generation**: Provide users with the anonymized text, extracted named entities, readability score, and corrected text if applicable.
8. **Optional Features**: Consider adding language translation using Charles Translator included in 'anonymize-mcp', and the ability to save outputs in various formats like .txt, .pdf, or .docx.

Ensure the application is user-friendly, efficient, and adheres to non-commercial usage guidelines set by 'anonymize-mcp'.