Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/misonl/ling/mcp-buildernpx skills add MisonL/Ling --skill mcp-buildergit clone --depth 1 https://github.com/MisonL/LingWrote 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.
[](https://agentmods.dev/skills/misonl/ling/mcp-builder)<a href="https://agentmods.dev/skills/misonl/ling/mcp-builder"><img src="https://agentmods.dev/badge/skills/misonl/ling/mcp-builder.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00025 | $0.00944 |
| Opus 5 | $0.00013 | $0.00472 |
| Sonnet 5 | $0.00005 | $0.00189 |
| Haiku 4.5 | $0.00003 | $0.00094 |
Grade A, and why
mcp-builder 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 4d 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.
What it actually says
MCP 构建器
MCP 服务器构建原则。
1. MCP 概览
什么是 MCP？
Model Context Protocol：用于连接 AI 系统与外部工具、数据源的标准协议。
核心概念
| 概念 | 目的 |
|---|---|
| Tools | AI 可调用的函数能力 |
| Resources | AI 可读取的数据资源 |
| Prompts | 预定义提示词模板 |
2. 服务架构
项目结构
my-mcp-server/
+-- src/
| +-- index.ts # 主入口
+-- package.json
+-- tsconfig.json
传输类型
| 类型 | 用途 |
|---|---|
| Stdio | 本地、CLI 场景 |
| SSE | Web 场景、流式输出 |
| WebSocket | 实时、双向通信 |
3. 工具设计原则
优秀工具设计
| 原则 | 描述 |
|---|---|
| 名称清晰 | 动作导向（get_weather, create_user） |
| 单一职责 | 一次只做好一件事 |
| 输入可校验 | 使用含类型与描述的 schema |
| 输出结构化 | 响应格式可预测 |
输入 Schema 设计
| 字段 | 必填？ |
|---|---|
| Type | 是（object） |
| Properties | 定义每个参数 |
| Required | 列出必填参数 |
| Description | 人类可读说明 |
4. 资源模式
资源类型
| 类型 | 用途 |
|---|---|
| Static | 固定数据（配置、文档） |
| Dynamic | 按请求动态生成 |
| Template | 含参数的 URI 模板 |
URI 模式
| 模式 | 示例 |
|---|---|
| Fixed | docs://readme |
| Parameterized | users://{userId} |
| Collection | files://project/* |
5. 错误处理
错误类型
| 情况 | 响应 |
|---|---|
| 参数无效 | 返回明确的校验错误 |
| 资源不存在 | 返回清晰的 “not found” |
| 服务器错误 | 返回通用错误并记录日志 |
最佳实践
- 返回结构化错误对象
- 不暴露内部实现细节
- 记录可追踪日志用于调试
- 提供可执行的错误提示
6. 多模态处理
支持类型
| 类型 | 编码 |
|---|---|
| Text | Plain text |
| Images | Base64 + MIME type |
| Files | Base64 + MIME type |
7. 安全原则
输入校验
- 校验所有工具输入
- 清洗用户提供的数据
- 限制资源访问范围
API 密钥
- 使用环境变量存储
- 禁止日志输出密钥
- 校验调用权限
8. 配置
Claude Desktop 配置
| 字段 | 目的 |
|---|---|
| command | 要执行的命令 |
| args | 命令参数 |
| env | 环境变量 |
9. 测试
测试类别
| 类型 | 关注点 |
|---|---|
| Unit | 工具逻辑 |
| Integration | 服务整体 |
| Contract | Schema 校验 |
10. 最佳实践检查清单
- 工具名称清晰且动作导向
- 输入 schema 完整且含说明
- 输出为结构化 JSON
- 覆盖各类错误处理场景
- 输入校验到位
- 使用环境变量进行配置
- 日志可用于排障与调试
记住： MCP 工具应保持简单、聚焦且文档完善。AI 依赖描述来正确调用它们。
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.
- 4d ago First seen · 177 lines · 25 tokens per session scan A 1f90ff923d8e
mcp-builder is a skill published in the GitHub repository MisonL/Ling (8 stars, last pushed 5mo ago), licensed MIT. It adds 25 tokens to every session and 944 once invoked, about $0.0001 per session on Opus 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…