Proxies MCP traffic in real time, analyses tool call behaviour and detects malicious tools or agent actions.
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- AAgentAvowAgentAvow官方Checks whether a tool, MCP server, package or skill is safe to connect and returns a signed, verifiable safety grade with reasons.安全5 仓库星标
- MMastyfmastyf-ai官方Security proxy for LLMs and MCP that blocks prompt injection, SSRF, injection attacks and credential exfiltration.安全21 仓库星标
- RReasonGatecgrtmlGateway for stdio MCP servers that blocks tool calls whose destination or content came from untrusted tool results, with an auditable reason for each decision.安全16 仓库星标
- AAegisgetaegisLocal proxy that injects API keys at the network boundary so agents never see them, with domain limits and audit logs.安全14 仓库星标
- AAssayRul1anPolicy proxy for MCP tool calls that denies risky calls and records decisions in offline-verifiable evidence bundles.安全13 仓库星标
- Amcp-auditp4st4sTransparent Go proxy that intercepts, signs, rate-limits, redacts and audits MCP tool calls between any client and server.安全8 仓库星标