# bad-mcp

> bad-mcp — ytkoka-bad-mcp. Use this tool when you need to simulate common attack patterns and evaluate detection capabilities. It provides a harness for building test MCP servers, accepting inputs via streaming HTTP or stdio, and outputs data for detection evaluation. Ideal for security testing and threat detection assessment in various network environments.

Canonical page: https://skillsregistry.net/skills/ytkoka-bad-mcp  
JSON: https://api.skillsregistry.net/v1/skills/ytkoka-bad-mcp

## Description

A harness for building test MCP servers that reproduce common attack patterns, enabling detection evaluation via streaming HTTP or stdio.

## Trust

- **Trust score (0–1):** 0.68
- **Verification tier:** scanned
- **Last scanned:** 2026-08-29

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** other
- **Updated:** 2026-08-29

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/lptelnknmr)
- **Repository:** <https://github.com/ytkoka/bad-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": "ytkoka-bad-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/ytkoka-bad-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/ytkoka-bad-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