# My MCP Server

> Use this tool when you need to demonstrate a vulnerable MCP server setup and test prompt injection detection capabilities. It solves problems related to securing add tools from malicious input and provides a test environment for evaluating detection mechanisms. The tool accepts input in the form of user prompts and outputs detection results, making it ideal for cybersecurity testing and research contexts.

Canonical page: https://skillsregistry.net/skills/sonnylabs-mcp-server-example  
JSON: https://api.skillsregistry.net/v1/skills/sonnylabs-mcp-server-example

## Description

Demonstrates an MCP server with a vulnerable add tool protected by SonnyLabs prompt injection detection.

## Trust

- **Trust score (0–1):** 0.78
- **Verification tier:** scanned
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-19

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/gaziaxbifa)
- **Repository:** <https://github.com/SonnyLabs/mcp_server_example>

## 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": "sonnylabs-mcp-server-example"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/sonnylabs-mcp-server-example` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/sonnylabs-mcp-server-example/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