# io.github.nexus-api-lab/nexus-mcp

> Use this tool when you need to protect Japanese language models from security threats, specifically prompt injection attacks and sensitive data exposure. It provides core functionality for detecting and preventing malicious prompt injections (jpi-guard) and masking personally identifiable information (PII Guard). Ideal for applications requiring secure and private Japanese language processing, with inputs including text prompts and outputs featuring safeguarded responses.

Canonical page: https://skillsregistry.net/skills/io-github-nexus-api-lab-nexus-mcp  
JSON: https://api.skillsregistry.net/v1/skills/io-github-nexus-api-lab-nexus-mcp

## Description

Japanese LLM security — prompt injection detection (jpi-guard) + PII masking (PII Guard). Free.

## Trust

- **Trust score (0–1):** 0.97
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-28

## Source

- **Source listing:** [MCP Registry](https://registry.modelcontextprotocol.io/v0/servers/io.github.nexus-api-lab%2Fnexus-mcp)
- **Repository:** <https://github.com/nexus-api-lab/nexus-mcp>

## Use it

MCP endpoint published by the skill: `https://mcp.nexus-api-lab.com/`

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": "io-github-nexus-api-lab-nexus-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/io-github-nexus-api-lab-nexus-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/io-github-nexus-api-lab-nexus-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