"Firefly III" matching MCP connectors:

Scans text for personally identifiable information — emails, phone numbers, SSNs, credit card numbers, physical addresses, names — and returns a redacted version. Built for agents sanitizing user content, support tickets, logs, or documents before storage, sharing, or feeding into another LLM call. Pay-per-call via x402 (USDC on Base): $0.01/call, no account or API key. tools/list and /openapi.json are free for discovery.

Two LLM security APIs for Japanese applications. (1) jpi-guard — Prompt Injection Detection Detects and blocks prompt injection attacks before they reach your LLM. Specialized for Japanese: full-width character bypass (全角バイパス), polite-language disguise (丁寧語擬装), indirect injection, Base64 obfuscation. (2) PII Guard — Japanese PII Detection & Masking Scans text for 10 PII categories.

Sanitize PII from text before it reaches LLMs. Redacts emails, phone numbers, national IDs, private keys, and financial data. Supports EN, ES (LATAM), PT (BR/PT), DE, JA. No authentication required — single POST request.