Local MCP layer for coding agents that redacts detected secrets from file reads and command output before they reach the model.
Setup
This project documents no single launch command; follow its repository instructions.
Fida
ajipurn
Related
More- CCodeInspectusSynvoyaLocal security scanner for AI-generated JS/TS apps that combines Opengrep, Gitleaks and Trivy with checks for secrets, Supabase RLS and prompt injection.Security49 Repository stars
- SServeMyAPIJktfeStores and retrieves API keys across projects in the macOS Keychain so assistants can fetch credentials by name.Security25 Repository stars
- Ss-gwsgatewayLocal credential gateway for coding agents: agents get handles instead of raw secrets, and approved commands get credentials injected locally.Security15 Repository stars
- AAegisgetaegisLocal proxy that injects API keys at the network boundary so agents never see them, with domain limits and audit logs.Security14 Repository stars
- CCodeGuard 代码安全扫描工具mcpdevChina实时扫描 AI 生成的代码，检测其中的漏洞、泄露的密钥和合规问题SecurityRemote only
- KkeystashTHUboranChina让智能体管理 API key、token 等密钥却看不到明文：值存于 macOS 钥匙串，可注入命令或调用预先批准的地址。Security