Model Scanner MCP server

by 4hmetuyar·io.github.4hmetuyar/model-scanner·v0.1.2·1 stars

Scans ML model files (PyTorch, safetensors, Keras, ONNX) for supply-chain risks

B78/100grade B

What users say

No reviews yet

Safety scan

B78/100

Adoption

Growing

1 stars522 downloads/wk

Reviews

Nobody has reviewed Model Scanner yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

list_patterns
List every dangerous Python global (module.function) this scanner treats as a red flag when found referenced inside a pickled model file, grouped by risk category
scan_directory
Recursively scan a directory for ML model files (.pt, .pth, .ckpt, .pkl, .pickle, .bin, .safetensors, .h5, .hdf5, .keras, .onnx) and report supply-chain risks in each. Automatically skips node_modules, .git, venv, and other non-model directories.
scan_file
Scan a single ML model file for supply-chain risks: dangerous Python globals reachable during pickle deserialization (os/subprocess/eval/socket/etc, including inside PyTorch's zip checkpoint container), a malformed or disguised .safetensors header, a Keras Lambda-layer RCE pattern in .h5/.keras files, or a path-traversal external_data reference in .onnx files.

scanner v0.1.10 · 2026-10-01 · same rubric, same numbers if you re-run it

1 medium

Code scan25 source files scanned20/25
–Live reliabilityno gateway calls yet and no remote to proben/a
–Tool poisoningtools not inspected (local package is not executed); not countedn/a
Auth qualitylocal package, no credentials required12/15
Maintenancelast push 0 days ago15/15
Maintainer identitynamespace and repository owner differ4/10

mediumeval / new Function usedexec.eval

dist/safetensorsScanner.js: …am code path (e.g. a custom loader that eval()s a metadata field), this content is wo…

Overall 78/100. Components that don't apply are left out of the denominator. Any critical finding is an F.Rubric Appeal a finding JSON

Runs npx -y @guardbee/mcp-model-scanner on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add model-scanner -- npx -y @guardbee/mcp-model-scanner

From the Model Scanner repository's README, as published. We do not edit it. Read it on GitHub

🇬🇧 English | 🇹🇷 Türkçe | 🇨🇳 中文

guardbee.ai — AI Security Copilot for websites.

GuardBee's family of MCP (Model Context Protocol) servers — a single monorepo, independent npm packages.

Nothing above is checked by us. What we check is on the safety report.

Is Model Scanner MCP server safe?: Mostly: it is graded B (78/100). Read the Model Scanner safety report
How do I install Model Scanner?: It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Model Scanner need an API key?: Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Model Scanner maintained?: The last commit was 12 days ago (2026-10-01). The latest release is v0.1.2.
What can I use instead of Model Scanner?: Servers from other publishers that do the same job: Skillsmith MCP server, Agent Security Scanner MCP server and Basic Memory MCP server. Compare all Model Scanner alternatives.

Same job from other publishers: the closest match first, then the best rated.

Skillsmith
Share agent skills across your team, scan them for risk, and track what's actually used.
not reviewed
Established
B
Agent Security Scanner
Security layer for AI agents: blocks prompt injection, detects fake packages, scans vulnerabilities.
not reviewed
Established
C
Basic Memory
Local-first knowledge management with bi-directional LLM sync via Markdown files.
not reviewed
Established
C
VisualTorch
Render PyTorch architecture diagrams and animated GIF reveals from trusted model source.
not reviewed
Established
A
Openflowkit
Architecture diagrams for your agent: draw on the live OpenFlowKit canvas or edit diagram files.
not reviewed
Established
A