# MCPAudit

> MCPAudit — saagpatel-mcpaudit. Use this tool when you need to identify security vulnerabilities and configuration issues in your MCP servers. It audits locally configured servers for permission risks, prompt injection threats, and schema drift, providing insights to mitigate potential threats. Input includes access to local MCP server configurations, with output being a comprehensive audit report highlighting areas of risk and recommended remediations.

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

## Description

Audit all locally configured MCP servers for permission risks, prompt injection threats, and schema drift

## Trust

- **Trust score (0–1):** 0.62
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

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

## Source

- **Source listing:** [GitHub](https://github.com/saagpatel/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": "saagpatel-mcpaudit"
    }
  }
}
```

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