広告掲載
MCP.so
ログイン

nexus-mcp — jpi-guard & PII Guard MCP Server

@nexus-api-lab

リポジトリ

基本情報

カテゴリ

その他

トランスポート

stdio

作者

nexus-api-lab

投稿者

dokasuka don

nexus-mcp — jpi-guard & PII Guard MCP Server について

Japanese LLM security APIs — prompt injection detection (jpi-guard) + PII masking (PII Guard). Free to start, no credit card required.

#security#prompt-injection#japanese#llm#rag#pii#ai-safety

nexus-mcp — jpi-guard & PII Guard MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "nexus-mcp": {
      "url": "https://mcp.nexus-api-lab.com/mcp"
    }
  }
}

nexus-mcp — jpi-guard & PII Guard MCP Server のツール

6

Detect prompt injection attacks (Japanese + English)

Validate RAG user input before passing to LLM

Sanitize external content before injection into prompts

Detect and mask PII (10 categories, Japanese-aware)

Issue a free trial API key (2,000 requests)

Issue a PII Guard trial key

概要

What is nexus-mcp — jpi-guard & PII Guard?

nexus-mcp — jpi-guard & PII Guard is an MCP server that protects LLM pipelines from prompt injection and PII leaks. It provides Japanese‑aware security tools for developers and operators.

How to use nexus-mcp — jpi-guard & PII Guard?

Add the following configuration to your MCP client and connect. No API key is required to start; a free trial of 2,000 requests is included. Use the provided tools (e.g., check_injection, pii_scan) via the MCP interface.

{
  "mcpServers": {
    "nexus-mcp": {
      "url": "https://mcp.nexus-api-lab.com/mcp"
    }
  }
}

Key features of nexus-mcp — jpi-guard & PII Guard

  • Detect prompt injection in Japanese and English
  • Validate RAG user input before LLM processing
  • Sanitize external content before prompt injection
  • Detect and mask 10 categories of PII (Japanese‑aware)
  • Issue free trial API keys (2,000 requests)
  • Issue separate PII Guard trial keys

Use cases of nexus-mcp — jpi-guard & PII Guard

  • Prevent prompt injection attacks in multilingual chat applications
  • Ensure RAG pipelines receive safe, validated user queries
  • Sanitize scraped or third‑party content before feeding to an LLM
  • Mask personally identifiable information in Japanese text before storage or logging
  • Rapidly prototype security‑hardened LLM workflows with a free trial key

よくある質問

1

What tools does the server provide?

Six tools: `check_injection`, `validate_rag_input`, `sanitize_content`, `pii_scan`, `get_trial_key`, and `get_pii_guard_key`. Each is described in the README.

2

Do I need an API key to start?

No. The server works without an initial API key; a free trial of 2,000 requests is available.

3

What languages are supported for injection and PII detection?

Prompt injection detection supports Japanese and English. PII scanning is Japanese‑aware.

4

How do I obtain a trial key?

Use the `get_trial_key` tool to issue a free trial key (2,000 requests) or `get_pii_guard_key` for a PII Guard trial key.

コメント

「その他」の他のコンテンツ

Glasswarp

Glasswarp

See and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.

Figs, Relationship Expert

Figs O'Sullivan, LMFT

Couples therapist Figs O'Sullivan (LMFT, 17 years, endorsed by Sue Johnson, creator of EFT) inside your AI. Ask relationship questions answered from his clinical writing, name the pattern in a fight, get a three-step rep

Lemon.io

lemon-io

Request dedicated senior developers to work on your project, write job descriptions, and prep technical interviews — all without leaving your Claude chat. Just describe what you need, and Lemon.io MCP does the rest. 1–3

Klarix Intelligence Engine

Klarix

B2B competitive intelligence, live sales battlecards, 5-axis ICP prospect fit scoring, and tech stack teardowns over MCP and REST with cited public-web evidence.

EverArt

modelcontextprotocol

Model Context Protocol Servers

88.1K
広告掲載