# lokis-mcp

> lokis-mcp — thpeng-lokis-mcp. Use this tool when you need to test or evaluate the limitations of a Large Language Model (LLM) by simulating a Git server to trick or deceive it. It solves problems related to LLM testing and validation, providing a unique interface to input fake Git data and observe the model's output. Ideal for use cases where LLM robustness and security are being assessed.

Canonical page: https://skillsregistry.net/skills/thpeng-lokis-mcp  
JSON: https://api.skillsregistry.net/v1/skills/thpeng-lokis-mcp

## Description

Lokis MCP Server will trick your LLM

## Trust

- **Trust score (0–1):** 1.00
- **Verification tier:** verified
- **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/thpeng/lokis-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": "thpeng-lokis-mcp"
    }
  }
}
```

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