# com.cognivators/mcp-safeguard

> Use this tool when you need to secure your MCP server from potential threats, as it detects and prevents issues such as prompt injection, credential leaks, Server-Side Request Forgery (SSRF), and tool poisoning. It scans the server to identify vulnerabilities, providing outputs that highlight potential security risks. Ideal for use in environments where server security is a top priority, this tool helps protect against common web application attacks.

Canonical page: https://skillsregistry.net/skills/com-cognivators-mcp-safeguard  
JSON: https://api.skillsregistry.net/v1/skills/com-cognivators-mcp-safeguard

## Description

MCP server security scanner: detects prompt injection, credential leaks, SSRF, tool poisoning.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** unverified

## Facts

- **Version:** 0.3.2
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-06-12

## Source

- **Source listing:** [MCP Registry](https://registry.modelcontextprotocol.io/v0/servers/com.cognivators%2Fmcp-safeguard)

## 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": "com-cognivators-mcp-safeguard"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/com-cognivators-mcp-safeguard` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/com-cognivators-mcp-safeguard/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