Nexus Mcp

Connects Claude to two Japanese LLM security APIs over HTTP: jpi-guard for prompt injection detection and PII Guard for masking sensitive data like My Number, credit cards, and phone numbers. Exposes tools like check_injection (returns is_injection, risk_level, detection_reason), sanitize_content (cleans external text before RAG context injection), and pii_scan (finds and masks PII with placeholder tags). Both APIs issue free trial keys directly through MCP tool calls, no signup required. Useful if you're building Japanese chatbots or RAG pipelines and need a deterministic security gate before user input hits the model or before storing conversation logs with personal information.