A policy firewall for AI-agent tool calls (MCP). Allow/deny/redact every tool call, with tamper-evident audit logging and NIST/OWASP control mapping.
接入配置
该项目没有提供统一的启动命令，请按源码仓库的说明安装。
相关推荐
更多- Ppacket-tracer-mcpJcorderop02MCP server for Cisco Packet Tracer 9 — let Claude/ChatGPT design, build and validate Cisco network topologies in real time (OSPF, BGP, VLAN, NAT, VoIP, QoS, IPv6, wireless). 57 MCP tools, live HTTP bridge, TypeScript on Bun.开发工具14 仓库星标
- Ttribuia-taller-seguridadandrescaicedomEntorno de pentesting reproducible con aplicación web intencionalmente vulnerable (aproximadamente 30 vectores en tres capas: aplicación, datos e infraestructura). Diseñado para aprender seguridad ofensiva y defensiva usando Claude Code y Gemini CLI como agentes de pentesting via MCP.开发工具5 仓库星标
- Ssf-intelligence: offline Salesforce MCP serverPranavNagrechaKnow what breaks before you change Salesforce. Ask your AI about your org: where a field is used, what runs on save, which Apex is dead, who can see what. Offline, read-only, cited. Open source (MIT).开发工具2 仓库星标
- Ttrajectory-eval-harnessxy9iaoEvaluation framework for LLM-agent reliability — scores intermediate reasoning steps, not just final outputs. Demonstrated on a resume–JD screening agent with a human-in-the-loop gate. Trajectory-level scorers, pass^k stability, and prompt-injection rounds across 2 model providers.开发工具2 仓库星标
- AabilityguardibrahimhajjajSnapshot, audit, and rollback middleware for the WordPress Abilities API.开发工具1 仓库星标
- MMSDefender-MCPllallumMCP Server for Defender XDR. No API Token Needed!!! Only Browser Session.开发工具1 仓库星标