# mcpaudit

> mcpaudit — axiorank-mcpaudit. Use this tool when you need to scan MCP servers for security vulnerabilities, such as prompt injection, tool poisoning, and leaked secrets, and generate SARIF reports that can be integrated with GitHub Actions. It provides a simple, keyless solution for identifying potential security threats. Ideal for use in git-based development workflows to ensure server security and integrity.

Canonical page: https://skillsregistry.net/skills/axiorank-mcpaudit  
JSON: https://api.skillsregistry.net/v1/skills/axiorank-mcpaudit

## Description

Scan any MCP server for prompt injection, tool poisoning, and leaked secrets. One command, no key. SARIF + GitHub Action.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

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

## Source

- **Source listing:** [GitHub](https://github.com/AxioRank/mcpaudit)

## 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": "axiorank-mcpaudit"
    }
  }
}
```

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