2
total weekly downloads
4 packages
safeprompt
API-first prompt injection protection for AI applications
@safeprompt.dev/langchain
LangChain integration for SafePrompt: prompt-injection detection as a callback handler. Validates every prompt flowing through a chain before it reaches the LLM.
@safeprompt.dev/mcp
Model Context Protocol (MCP) server for SafePrompt — gives any MCP-compatible AI agent a tool to detect prompt injection, jailbreaks, and code injection in untrusted text before it reaches an LLM.
safeprompt-middleware
Vendor-neutral AI security middleware for Express and Next.js. Works with any ai-security-gateway-spec compliant provider.