What is GPU-Server-Management-MCP-Skill- CLAUDE.md?

Project instructions for building and deploying a service that manages GPU servers through Cloudflare Workers, a database, and a remote tool interface. They describe the code layout, development commands, and available server-management operations.

Use them when developing, testing, deploying, or maintaining the GPU server management service and its web API, database, and tool interface.

They give contributors a shared procedure for running checks, applying database changes, testing, and deploying without guessing how the system is organized.

How ixijxjgxidj-cmd/GPU-Server-Management-MCP-Skill- configures Claude

Reuse

Borrowing it

Nothing to install: this file belongs to ixijxjgxidj-cmd/GPU-Server-Management-MCP-Skill-. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/ixijxjgxidj-cmd/GPU-Server-Management-MCP-Skill-/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/ixijxjgxidj-cmd/GPU-Server-Management-MCP-Skill-

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/ixijxjgxidj-cmd/gpu-server-management-mcp-skill-/claude-md/github.svg)](https://agentmods.dev/instructions/ixijxjgxidj-cmd/gpu-server-management-mcp-skill-/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/ixijxjgxidj-cmd/gpu-server-management-mcp-skill-/claude-md"><img src="https://agentmods.dev/badge/instructions/ixijxjgxidj-cmd/gpu-server-management-mcp-skill-/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/ixijxjgxidj-cmd/gpu-server-management-mcp-skill-/claude-md"><img src="https://agentmods.dev/badge/instructions/ixijxjgxidj-cmd/gpu-server-management-mcp-skill-/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,868 This file is loaded in full into every session.

When invoked 1,868 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.01868	$0.01868
Opus 5.5	$0.00747	$0.00747
Sonnet 5.5	$0.00374	$0.00374
Haiku 4.5	$0.00187	$0.00187

Measured 2mo ago against content hash e5a826191b01, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

GPU-Server-Management-MCP-Skill- CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md - GPU Server Management MCP & Cluster Protocol

Target Platform: Cloudflare Workers + Cloudflare D1 Database + Streamable HTTP MCP (JSON-RPC 2.0)
Skill Name: gpu-server-management
Server Name: gpu-mcp-server-cf

🚀 Quick Development & Deployment Commands

# 进入 Worker 项目目录
cd gpu-mcp-server-cf

# 本地调试
npm run dev

# 编译类型检查
npx tsc --noEmit

# 部署到 Cloudflare Workers
npm run deploy  # 或 npx wrangler deploy

# 应用 D1 数据库迁移 (远程生产库)
npx wrangler d1 migrations apply DB --remote

# 运行单元测试
npm test

🏛 系统架构与目录规范

gpu-mcp-server-cf/: Cloudflare Workers 后端核心源码
- src/index.ts: Hono 应用入口与路由分发 (/mcp, /api/*, /)
- src/mcp/: 18 个 MCP 工具的 schema 与执行处理器
- src/db/: D1 数据库 schema、SQL 迁移脚本与查询封装
- src/api/: REST API（服务器、代理池、NVIDIA NIM、排错知识库、状态探针）
- src/frontend/html.ts: 响应式 Web 控制台单文件前端（HTML/CSS/JS）
.agents/skills/gpu-server-management/: Agent 技能指令集与最佳实践

🛠 18 个核心 MCP 工具一览

分类	工具名称	作用
连接与生命周期	`get_servers`	获取可用节点列表、Base64 密钥、实时负载、预存数据集、倒计时、跳板机标识及避坑经验 (`pitfalls`)
	`claim_server`	声明占用服务器，锁定任务并设定倒计时租期 (`duration_minutes`)
	`release_server`	任务完成或异常退出后主动释放算力
调度与智能备份	`plan_server_backup`	双模智能分流备份（充足期仅备产出 vs. 临期全量撤离），自动同步 MCP RAG 向量库
	`query_backup_index`	自然语言/指标关键词 RAG 检索历史备份记录（绑定 IP 生命周期）
	`plan_task_allocation`	多任务多维装箱调度（数据集亲和性 `Dataset Affinity` 享 +100,000 分置顶）
	`register_dataset`	登记服务器已缓存的数据集路径与大小，写入集群集体记忆
	`remove_dataset`	移除已删除或卸载的数据集元数据记录
	`plan_disk_share`	磁盘不足时计算并生成 `sshfs`/`nfs` 跨机挂载指令
	`plan_network_relay`	生成直连 vs. 代理并发毫秒测速竞速脚本与 >500MB 分片聚合拉取命令
	`refresh_load`	下发实时物理负载探测命令 (`nvidia-smi`, `free`, `df`)
注册与集体记忆	`upsert_server`	注册/更新服务器（以 host 唯一去重），写回运维避坑笔记 (`notes_entry`) 与跳板机开关
	`update_server`	修改服务器字段（包含 `is_jump_host`、上下架状态等）
	`remove_server`	永久移除服务器（级联清理该 IP 下关联的所有备份索引）
诊断与代理池	`verify_server_connectivity`	测试直连 SSH 与代理可达性
	`import_proxy_subscription`	一键导入 Clash/V2Ray 订阅链接，自动解析批量录入代理池
	`list_proxies`	列出当前配置的所有 SOCKS5 / HTTP 代理节点
	`add_proxy`	添加单个代理节点
	`remove_proxy`	移除失效代理节点

Read the full file on GitHub · 120 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 120 lines · 1,868 tokens per session scan A e5a826191b01

Subscribe to this mod's changes

GPU-Server-Management-MCP-Skill- CLAUDE.md is an instructions file published in the GitHub repository ixijxjgxidj-cmd/GPU-Server-Management-MCP-Skill- (7 stars, last pushed 2mo ago), licensed MIT. It adds 1,868 tokens to every session, about $0.0075 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Cloud DevOps and cloud Hardware and IoT

GPU-Server-Management-MCP-Skill- CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
GPU-Server-Management-MCP-Skill- CLAUDE.mdixijxjgxidj-cmd/GPU-Server-Management-MCP-Skill-	Instructions file	7	2mo ago	MIT	A	1,868	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

GPU-Server-Management-MCP-Skill-: Instructions file for Claude Code