Show HN: MCPShark – 模型上下文协议流量检查器

13作者: mywork-dev21 天前
GitHub 链接:<a href="https:&#x2F;&#x2F;github.com&#x2F;mcp-shark&#x2F;mcp-shark" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;mcp-shark&#x2F;mcp-shark</a> 网站:<a href="https:&#x2F;&#x2F;mcpshark.sh&#x2F;" rel="nofollow">https:&#x2F;&#x2F;mcpshark.sh&#x2F;</a> 我开发了 MCPShark,一个用于模型上下文协议 (MCP) 的流量检查工具。 它位于你的编辑器/LLM 客户端和 MCP 服务器之间,你可以: * 在一个地方查看所有 MCP 流量(请求、响应、工具、资源) * 在工具行为异常时调试会话 * 可选地运行“智能扫描”检查,以标记有风险的工具/配置
查看原文
<a href="https:&#x2F;&#x2F;github.com&#x2F;mcp-shark&#x2F;mcp-shark" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;mcp-shark&#x2F;mcp-shark</a> Site: <a href="https:&#x2F;&#x2F;mcpshark.sh&#x2F;" rel="nofollow">https:&#x2F;&#x2F;mcpshark.sh&#x2F;</a><p>I built MCPShark, a traffic inspector for the Model Context Protocol (MCP).<p>It sits between your editor&#x2F;LLM client and MCP servers so you can: • See all MCP traffic (requests, responses, tools, resources) in one place • Debug sessions when tools don’t behave as expected • Optionally run “Smart Scan” checks to flag risky tools &#x2F; configs