bg-vanish-mcp

v0.1.0 suspicious
6.0
Medium Risk

MCP server for removing image backgrounds locally using rembg and DirectML

🤖 AI Analysis

Final verdict: SUSPICIOUS

The package has a moderate risk score due to its recent upload and lack of maintainer history, raising concerns about its legitimacy and potential for malicious intent.

  • Recent upload with no maintainer history
  • Missing author details
Per-check LLM notes
  • Network: No network calls detected, which is normal unless the package's functionality requires external API interactions.
  • Shell: No shell execution patterns detected, indicating no immediate risk of command injection or similar attacks.
  • Obfuscation: The use of base64 decoding for images may indicate an attempt to hide the nature of the data, but it could also be legitimate for various reasons such as transferring images as strings.
  • Credentials: No clear patterns indicating credential harvesting were found.
  • Metadata: The package is suspicious due to its recent upload, lack of maintainer history, and missing author details.

🔬 Heuristic Checks

Outbound Network Calls

No suspicious network call patterns found

Code Obfuscation score 2.0

Found 1 obfuscation pattern(s)

  • se64 image img_data = base64.b64decode(image_base64) input_image = Image.open(io.BytesIO(im
Shell / Subprocess Execution

No shell execution patterns detected

Credential Harvesting

No credential harvesting patterns detected

Typosquatting

No typosquatting candidates detected

Registered Email Domain

No author email provided

Suspicious Page Links

All external links appear legitimate

Git Repository History

No GitHub repository linked

  • No GitHub repository link found
Maintainer History score 10.0

5 maintainer concern(s) found

  • Only one version has ever been released — brand new package
  • Package uploaded less than 24 hours ago (2026-06-05T06:17:33.000Z)
  • Author name is missing or very short
  • Author "" appears to have only 1 package on PyPI (new or inactive account)
  • Package has no PyPI classifiers (low effort / metadata quality)