MCP-gateway-scan read-only scanner for MCP production-readiness
Seven-dimension security scoring catches fail-open errors before your MCP gateway hits production.
A lightweight, highly secure AI API Gateway/Proxy written in Go. Acts as transparent middleware between local AI coding clients (OpenCode/Pi/Cursor) and upstream LLM providers (Gemini, DeepSeek, Zhipu z.ai).
Secret redaction and MCP tool integration for Cursor and similar AI clients.
Developers using AI coding assistants like Cursor, OpenCode, Aider
LiteLLM · OpenRouter · Portkey
Seven-dimension security scoring catches fail-open errors before your MCP gateway hits production.
Synchronous HITL approvals for MCP agents solve the production trust gap nobody else addresses.
Bidirectional scanning catches response-side attacks when 28 other MCP tools only check requests.
IETF-backed security proxy for MCP agents when the protocol has none.
Yet another PII redaction proxy when Lakera and Portkey already dominate this space.
MCP-specific guardrails when Claude ecosystem lacks native security scanning.