# scan-mcp

> scan-mcp — cyreslab-ai-scan-mcp. Use this tool when you need to identify security vulnerabilities in MCP servers, such as tool poisoning, injection, and secrets exposure. It scans for issues in Dockerfiles and dependencies, providing outputs that highlight potential risks and weaknesses. Ideal for use in git-based development workflows to ensure secure server configurations.

Canonical page: https://skillsregistry.net/skills/cyreslab-ai-scan-mcp  
JSON: https://api.skillsregistry.net/v1/skills/cyreslab-ai-scan-mcp

## Description

Static security scanner for MCP servers — detects tool poisoning, injection, secrets, Dockerfile and dependency issues.

## Trust

- **Trust score (0–1):** 0.79
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/Cyreslab-AI/scan-mcp)

## 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": "cyreslab-ai-scan-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/cyreslab-ai-scan-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/cyreslab-ai-scan-mcp/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