skill-mcp-server

A set of patterns for building MCP servers in TypeScript or Python. MCP, the Model Context Protocol, lets AI clients call tools and read data exposed by a server.

In plain words
What is it for?
Use it to connect AI clients such as Claude Code or Cursor to APIs, databases, internal data, or actions through local or remote MCP servers.
Why use it?
It provides a defined way to structure tools, resources, prompts, validation, authorization, tracing, testing, and server connections.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/dewtech-technologies/dare-method/skill-mcp-server
Any agent
npx skills add dewtech-technologies/dare-method --skill skill-mcp-server
Clone the repo
git clone --depth 1 https://github.com/dewtech-technologies/dare-method

Made for: Claude Code, Codex.

Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,862 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00063 $0.02862
Opus 5 $0.00032 $0.01431
Sonnet 5 $0.00013 $0.00572
Haiku 4.5 $0.00006 $0.00286

Measured 2d ago against content hash 83611dd4cdaf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-mcp-server 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 2d 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.

implementations/antigravity/.agents/skills/skill-mcp-server/SKILL.md · 383 lines

How it starts

The opening of the file, as written. The whole thing — 383 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DARE MCP Server Skill

Você é um especialista em servidores MCP (Model Context Protocol da Anthropic). Seu papel é gerar servidores MCP bem estruturados, seguros, testáveis e publicáveis, expondo tools/resources/prompts via stdio, SSE ou HTTP.

Quando usar

  • Você precisa expor capacidades para Claude Code, Cursor ou outro cliente MCP
  • Você quer integrar uma API externa (Linear, GitHub, banco interno) como tool MCP
  • Você está auditando um servidor MCP existente

O que é MCP em 30 segundos

MCP (Model Context Protocol) é um protocolo aberto da Anthropic para conectar agentes a fontes de dados e ações externas. Um servidor MCP expõe:

  • Tools — funções chamáveis pelo agente (ex: create_issue, query_db)
  • Resources — dados leitáveis (ex: documentos, schemas)
  • Prompts — templates parametrizados

Transports suportados:

  • stdio — agente spawnea processo local, comunica via stdin/stdout (mais simples)
  • SSE — server remoto, agente conecta via Server-Sent Events
  • HTTP — server remoto stateless

Stack canônica (TypeScript)

  • Node 20+ com TypeScript 5.5+
  • @modelcontextprotocol/sdk SDK oficial
  • Zod para validação de input/output de tools
  • vitest para testes
  • eslint + prettier

Stack canônica (Python)

  • Python 3.11+
  • mcp SDK oficial (pip install mcp)
  • Pydantic v2 para schemas
  • pytest + pytest-asyncio
  • ruff + mypy

Estrutura recomendada (TypeScript)

mcp-meu-server/
├── package.json
├── tsconfig.json
├── src/
│   ├── index.ts                ← entrypoint (stdio)
│   ├── server.ts               ← criação do MCP Server
│   ├── tools/
│   │   ├── create_issue.ts
│   │   └── search_issues.ts
│   ├── resources/
│   │   └── schema.ts
│   ├── prompts/
│   │   └── issue_template.ts
│   ├── schemas/                ← Zod schemas
│   └── lib/
│       └── linear-client.ts    ← cliente da API externa
└── tests/

Exemplo: server stdio TypeScript

// src/index.ts
import { Server } from '@modelcontextprotocol/sdk/server/index.js';
import { StdioServerTransport } from '@modelcontextprotocol/sdk/server/stdio.js';
import { registerTools } from './tools/index.js';
import { registerResources } from './resources/index.js';

const server = new Server(
  { name: 'meu-mcp-server', version: '1.0.0' },
  { capabilities: { tools: {}, resources: {}, prompts: {} } }
);

registerTools(server);
registerResources(server);

const transport = new StdioServerTransport();
await server.connect(transport);

Read the full file on GitHub · 383 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.

  1. 2d ago First seen · 383 lines · 63 tokens per session scan A 83611dd4cdaf

Subscribe to this mod's changes

skill-mcp-server is a skill published in the GitHub repository dewtech-technologies/dare-method (5 stars, last pushed 1mo ago), licensed MIT. It adds 63 tokens to every session and 2,862 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

write-test-plan

Generate a QA/UAT test plan from product specifications and task definitions, covering acceptance testing, integration flows, and exploratory testing. Unit tests are out of scope (handled by write-unit-tests skill).

andresharpe/dotbot · 43 tokens

implement-telegram-bot

Implement Telegram bot interactions with command handlers, message parsing, and inline keyboards for conversational interfaces.

andresharpe/dotbot · 23 tokens

setup-background-job

Set up scheduled background jobs using Quartz.NET with proper configuration, error handling, and dependency injection.

andresharpe/dotbot · 22 tokens

write-unit-tests

Write comprehensive unit tests with proper setup, assertions, and coverage of happy paths, edge cases, and error scenarios.

andresharpe/dotbot · 26 tokens

blazor-component-design

Design Blazor components with proper parameter binding, event callbacks, lifecycle management, and render optimization. Use when creating new Blazor Server or WASM components, refactoring component hierarchies, implementing cascading values, or optimizing component rendering performance.

andresharpe/dotbot · 53 tokens

hedgehog-planning-intake

Use on any core for first-run planning intake — Phase 0 runs the vendored BMAD-METHOD planning shelf, shared by every core, and Phase 1 (mining 04-prd.md into intent records plus the Add-ons/sync-and-remote-entities decision) is full-stack-app's and pwa-app's shared procedure — identical mechanics, a different…

skyf0xx/hedgehog · 374 tokens