agentleFS
sunflowermmsunflowermm/XRK-AGT/.cursor/skills/xrk-mcp/SKILL.md

xrk-mcp

Skill140 starsChanged 8 months agoMITView on GitHub

当你需要理解或扩展 MCP 工具(注册/分组/远程连接)、执行门禁与 LLM tool calling 关系时使用。

The file

Files
SKILL.md

读者:Coding Agent。办事助手「怎么调某个工具」见 .xrk/skills/core/agent-tools。

文档与代码

docs/mcp-guide.md、docs/mcp-config-guide.md、core/system-Core/http/mcp.js、commonconfig/system/system-ai-workflow.js(ai-workflow.mcp)

要点

  • 工作流内 registerMCPTool → harness ToolRegistry(MCPToolAdapter)→ 执行仍进 MCPServer。
  • 执行前门禁统一在 MCPServer.handleToolCall → inspectToolCallSecurity(policies + toolScan + 可选审批);勿只在适配器拦一层。
  • 办事助手 / /v1+MCP 的 tool 环在 @xrkseek/harness;仅无 workflows 的 /v1 client-tools 走工厂透传。
  • 远程 MCP:ai-workflow.mcp.remote 或 workflow 模块 export function getMcpServers()(Loader → 插件 MCP 表);连接前 mcp.connect(checkMcpConnectAllowed)。HTTP 用 fetchWithPolicy(#utils/fetch-with-retry.js),无 RuntimeUtil.fetch。
  • 产品 Agent 挂远程:优先 JS getMcpServers,勿改系统 yaml(见 .xrk/skills/core/agent-core-dev §3.5)。
  • tools 增强:apply_edit / verify / repo_map / update_todos(实现 workspace/apply-edit-blocks.js · repo-map-lite.js)。

Node 26

  • MCP HTTP/远程连接走全局 fetch + AbortSignal.timeout;代理见 proxy-utils.js。
  • 工具 handler 判错用 Error.isError / normalizeError(skill xrk-node-runtime)。

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.