# Model Safety MCP

> Use this tool when you need to scan machine learning model artifacts for potential security threats, such as unsafe serialization or malicious patterns. It solves problems related to model safety by identifying risks and vulnerabilities, providing outputs that inform remediation efforts. Ideal for use cases involving model deployment, integration, or sharing, where security and reliability are critical.

Canonical page: https://skillsregistry.net/skills/itsalissonsilva-modelsafetymcp  
JSON: https://api.skillsregistry.net/v1/skills/itsalissonsilva-modelsafetymcp

## Description

ModelSafetyMCP is an MCP server for scanning machine learning model artifacts for unsafe serialization, malicious model patterns, risky packaging, URL-based artifact scanning, and directory-level triage.

## Trust

- **Trust score (0–1):** 0.60
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-05-05

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/bt0bhmqv27)
- **Repository:** <https://github.com/itsalissonsilva/ModelSafetyMCP>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "itsalissonsilva-modelsafetymcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/itsalissonsilva-modelsafetymcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/itsalissonsilva-modelsafetymcp/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt