Provides a local MCP server that exposes the check_prompt_injection tool to MCP clients, letting agents scan untrusted text (web pages, documents, tool outputs, emails) for prompt injection before passing it to another LLM.
A deterministic MCP server that guards AI/agent output by detecting secrets, injection, and PII in ~85µs with zero dependencies. Gives a clear ship/block verdict and runs locally or hosted.
Unified MCP safety server that detects prompt injection (75 patterns), scans LLM outputs for leaked secrets/PII, enforces API cost budgets, and creates signed audit trails. Zero ML dependencies, pure Python.
A Model Context Protocol server that lets AI agents and runtime firewalls call PromptShield-style safety checks for text, chat messages, prompts, tool inputs, and generated outputs.
