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 proxy server that sits between MCP clients and servers, providing authentication, tool discovery, caching, and guardrail enforcement to protect MCP servers from malicious inputs.
Security proxy that wraps any MCP server with bidirectional scanning for credential leaks, prompt injection, and tool description poisoning. Also provides an HTTP fetch proxy with a 9-layer scanner pipeline for capability-separated agent deployments.
A least-privilege enforcement proxy for MCP servers. It sits between MCP clients and upstream servers, enforcing tool policies, hiding denied tools, requiring human approval for risky actions, and providing a structured audit trail.