Overview
Spring AI Privacy Guardrails is a tool that keeps detected PII out of AI models. It tokenizes detected PII before sending it to a model, replacing each detected value with an opaque token that does not directly reveal the original value. It also limits which original values each tool may receive. The product includes an optional Spring Security integration that controls which tools are shown to the model and checks authorization before tool execution. This integration can be used independently of PII protection. A Privacy Boundary Inspector allows comparison of values received by the model and tools in Local Tool, RAG, and MCP scenarios, and comparison of tool access for users with different roles. The default sample uses a local ChatModel and requires no external model API key.
Pricing
Free
Detailed plans have not been confirmed in our catalog. Check the official website for current limits and billing terms.
Visit WebsitePrices and limits may change. Confirm the currency, billing period, seat minimum and usage caps on the official website.
Use Cases
- Teams use Spring AI Privacy Guardrails to tokenize detected PII before sending it to a model.
- Teams use Spring AI Privacy Guardrails to limit which original values each tool may receive.
- Teams use Spring AI Privacy Guardrails to control which tools are shown to the model and check authorization before tool execution.
- Teams use Spring AI Privacy Guardrails to compare the values received by the model and tools in Local Tool, RAG, and MCP scenarios.
- Teams use Spring AI Privacy Guardrails to compare tool access for users with different roles.
Features
Tokenize detected PII before model calls
Limit PII disclosure to individual tools
Control tool visibility by authorization
Check permissions before tool execution
Inspect model and tool data boundaries
Compare tool access across user roles
Reviews
No reviews yet. Be the first to share your experience!