convez.ai
MCP ServerDevOps & InfraestruturaIntermediário
starter-series

MCP Server Starter

starter-series/mcp-server-starter

Bootstrap de servidor MCP com TypeScript, OIDC publish e CI/CD zero-config

Ver no GitHub
BomPluginScore · de 0 a 100

Template pronto para desenvolvimento de servidores MCP (Model Context Protocol) com TypeScript, CI/CD automatizado e publicação OIDC no npm sem necessidade de secrets. Inclui padrões de segurança, validação com Zod e análise estática de código.

Instalação

$npx convez-ai starter-series/mcp-server-starter

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
0
Forks
0
Acompanhando
0
Saúde
87%
Último commit
há 6 dias
Versão
—
Issues abertas
14
Contribuidores
2

Casos de uso

  • Criar novo servidor MCP para integração com Claude
  • Publicar tools reutilizáveis no npm com pipeline seguro
  • Implementar recursos e prompts para o protocolo MCP

Veredito

Starter robusto e bem-estruturado para quem precisa lançar servidores MCP produção-ready. A cobertura de CI/CD com OIDC, segurança estática e padrões de validação elimina decisões arquiteturais repetitivas — ideal para times que valorizam ship-first com confiança.

README

A tradução para o português deste README ainda está na fila.

MCP Server Starter

TypeScript + OIDC npm Publishing + CI/CD.

Build your MCP server. One-click publish. Zero secrets needed.

CI License: MIT npm version

English | 한국어


Part of Starter Series — Stop explaining CI/CD to your AI every time. Clone and start.

Docker Deploy · Discord Bot · Telegram Bot · Browser Extension · Electron App · npm Package · React Native · VS Code Extension · MCP Server · Python MCP Server · Cloudflare Pages


About This Starter

Currently implemented

  • MCP SDK — @modelcontextprotocol/sdk with stdio transport
  • TypeScript — Strict mode (incl. noUncheckedIndexedAccess + verbatimModuleSyntax), ES2023 target, Zod-validated input & output schemas
  • Safety annotations — readOnly/destructive/idempotent hints on every tool
  • Prompts — Guided workflow templates via registerPrompt (SDK v1.29+)
  • Resources — Data exposure pattern with metadata + handler
  • Response helpers — ok() and err() for consistent tool responses
  • Config — Environment variable parsing pattern
  • CI — gitleaks, npm audit, license compliance, ESLint, build, test
  • CodeQL — Static security analysis (push/PR + weekly)
  • CD — OIDC trusted publishing to npm (zero secrets needed)
  • Dependabot — Automated dependency + GitHub Actions updates

Planned

Nothing on a public roadmap. The starter is intentionally finished; downstream projects extend it. Breaking-change waves (Node EOL, SDK majors) land via Dependabot.

Design intent

Bootstrap a publishable MCP server in under a minute. Stdio is the default because every local MCP client speaks it; HTTP transport is shown inline (see below) rather than bundled, to keep the dependency surface minimal. OIDC publishing means contributors never paste an npm token. Globally-unique tool names are enforced by convention — prefix with your module name, since name collisions across servers are the most common foot-gun.

Non-goals

  • Auth primitives, HMAC signing, rate-limiting, audit logging, human-in-the-loop infra. Those belong in a host, not a server template.
  • Express / HTTP transport in the default scaffold. Template stays small; HTTP is documented for those who need it.
  • Opinionated logging, tracing, or observability stack. Pick what fits downstream.

Redacted

None. Public template.

Quick Start

Via create-starter (recommended):

npx @starter-series/create my-mcp-server --template mcp-server
cd my-mcp-server && npm install && npm run dev

Or clone directly:

git clone https://github.com/starter-series/mcp-server-starter my-mcp-server
cd my-mcp-server && npm install && npm run dev

Adding Tools

Tool names must be globally unique across all MCP servers a client connects to. Prefix with your module name (e.g., mymodule_action instead of action).

Create src/tools/your-tool.ts:

import { z } from 'zod';
import { ok, err } from '../helpers.js';

export const name = 'your_tool';

export const config = {
  title: 'Your Tool',
  description: 'What your tool does',
  inputSchema: {
    input: z.string().describe('Input parameter'),
  },
  // Declare `outputSchema` to return structured results — the 2026 MCP spec
  // requires servers to populate `structuredContent` (validated against this
  // schema) alongside the text mirror. Omit `outputSchema` for free-form
  // text-only tools.
  outputSchema: {
    result: z.string().describe('Processed value'),
  },
  annotations: {
    readOnlyHint: true,
    destructiveHint: false,
    idempotentHint: true,
    openWorldHint: false,
  },
};

export async function handler({ input }: { input: string }) {
  try {
    const result = `Processed: ${input}`;
    // Pass the structured payload as the second arg to `ok()` — it's set as
    // `structuredContent` alongside the text mirror in `content[]`.
    return ok(result, { result });
  } catch (e) {
    return err(`Failed: ${e instanceof Error ? e.message : String(e)}`);
  }
}

Register in src/index.ts:

import * as yourTool from './tools/your-tool.js';
server.registerTool(yourTool.name, yourTool.config, yourTool.handler);

Adding Prompts

Prompts are reusable, parameterized message templates the client can surface to the user or feed to the model. Use registerPrompt (SDK v1.29+) for full control — title + description + Zod-validated argsSchema. See src/prompts/code-review.ts for a templated example.

Create src/prompts/your-prompt.ts:

import { z } from 'zod';

export const name = 'your-prompt';
export const title = 'Your Prompt';
export const description = 'Guided workflow description';

export const argsSchema = {
  param: z.string().min(1).describe('Required parameter'),
};

export function handler({ param }: { param: string }) {
  return {
    description,
    messages: [{
      role: 'user' as const,
      content: { type: 'text' as const, text: `Prompt text with ${param}` },
    }],
  };
}

Register in src/index.ts:

import * as yourPrompt from './prompts/your-prompt.js';
server.registerPrompt(
  yourPrompt.name,
  { title: yourPrompt.title, description: yourPrompt.description, argsSchema: yourPrompt.argsSchema },
  yourPrompt.handler,
);

Adding Resources

Resources expose data to the client (Tools perform actions). See src/resources/server-info.ts for a working example.

Create src/resources/your-resource.ts:

export const name = 'your-resource';
export const uri = 'info://your/resource';

export const metadata = {
  title: 'Your Resource',
  description: 'What this resource exposes',
  mimeType: 'application/json',
};

export async function handler(resourceUri: URL) {
  return {
    contents: [{ uri: resourceUri.href, mimeType: metadata.mimeType, text: '...' }],
  };
}

Register in src/index.ts:

import * as yourResource from './resources/your-resource.js';
server.registerResource(yourResource.name, yourResource.uri, yourResource.metadata, yourResource.handler);

HTTP Transport

This starter uses stdio (the standard for local MCP servers). If you need HTTP transport — for registries like Smithery/mcp.so or remote deployments — use StreamableHTTPServerTransport with Express:

import express from 'express';
import { randomUUID } from 'node:crypto';
import { McpServer } from '@modelcontextprotocol/sdk/server/mcp.js';
import { StreamableHTTPServerTransport } from '@modelcontextprotocol/sdk/server/streamableHttp.js';
import { isInitializeRequest } from '@modelcontextprotocol/sdk/types.js';

const app = express();
app.use(express.json());

const sessions = new Map<string, StreamableHTTPServerTransport>();

app.post('/mcp', async (req, res) => {
  const sessionId = req.headers['mcp-session-id'] as string;
  const existing = sessions.get(sessionId);

  if (existing) {
    await existing.handleRequest(req, res);
    return;
  }

  if (!isInitializeRequest(req.body)) {
    res.status(400).json({ error: 'Bad Request: Not an initialize request' });
    return;
  }

  const transport = new StreamableHTTPServerTransport({
    sessionIdGenerator: () => randomUUID(),
  });

  transport.onclose = () => {
    const id = transport.sessionId;
    if (id) sessions.delete(id);
  };

  const server = createServer(); // your McpServer factory
  await server.connect(transport);
  if (transport.sessionId) sessions.set(transport.sessionId, transport);
  await transport.handleRequest(req, res);
});

app.get('/mcp', async (req, res) => {
  const t = sessions.get(req.headers['mcp-session-id'] as string);
  if (!t) return res.status(400).end();
  await t.handleRequest(req, res);
});

app.delete('/mcp', async (req, res) => {
  const t = sessions.get(req.headers['mcp-session-id'] as string);
  if (!t) return res.status(400).end();
  await t.handleRequest(req, res);
});

app.listen(3000);

Why the complexity? Without isInitializeRequest, every POST creates a new transport → "Already connected" errors. Without GET, clients can't receive server notifications via SSE.

Stateless mode — if your server holds no per-session state (every tool call is independent), construct the transport with sessionIdGenerator: undefined and skip the session map. Stateless is simpler to deploy behind a stateless load balancer and is the recommended default for serverless hosts (Cloudflare Workers, Vercel functions). Keep the stateful pattern above only if you need server-initiated notifications or per-session caches.

See the MCP SDK docs for full details.

Testing Locally

MCP Inspector

npm run build
npx @modelcontextprotocol/inspector node dist/index.js

Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "my-mcp-server": {
      "command": "node",
      "args": ["/absolute/path/to/dist/index.js"]
    }
  }
}

After Publishing to npm

{
  "mcpServers": {
    "my-mcp-server": {
      "command": "npx",
      "args": ["-y", "my-mcp-server"]
    }
  }
}

CI/CD

CI (every push/PR)

  1. Secret scanning (gitleaks)
  2. Large file detection (>5 MB)
  3. License compliance (blocks GPL/AGPL)
  4. Security audit (npm audit)
  5. Lint (ESLint + TypeScript)
  6. Build (TypeScript compilation)
  7. Test (Jest)

Security & Maintenance

WorkflowWhat it does
CodeQL (codeql.yml)Static analysis for security vulnerabilities (push/PR + weekly)
Maintenance (maintenance.yml)Weekly CI health check — auto-creates issue on failure
Stale (stale.yml)Labels inactive issues/PRs after 30 days, auto-closes after 7 more

CD (manual trigger)

  1. CI gate (must pass)
  2. Version guard (prevents duplicate releases)
  3. npm publish with OIDC + provenance
  4. GitHub Release

Setup: See docs/NPM_PUBLISH_SETUP.md — trusted publishers configured on/after 2026-05-20 must select npm publish as an allowed action, or releases fail with an authorization error.

Project Structure

src/
├── index.ts              # Server entry — tool/resource/prompt registration + transport
├── config.ts             # Environment variable config
├── helpers.ts            # ok() / err() response helpers
├── tools/
│   └── greet.ts          # Example tool with annotations (replace with your own)
├── resources/
│   └── server-info.ts    # Example resource exposing server metadata (replace)
└── prompts/
    ├── hello.ts          # Zero-arg prompt example (replace with your own)
    └── code-review.ts    # Templated prompt with Zod-validated args
tests/
├── greet.test.js         # Tool tests
├── helpers.test.js       # Helper tests
├── server-info.test.js   # Resource tests
├── hello.test.js         # Prompt tests
└── code-review.test.js   # Templated prompt tests

Scripts

CommandDescription
npm run devRun with tsx (no build needed)
npm run buildCompile TypeScript
npm startRun compiled server
npm testBuild + run tests (pretest auto-builds)
npm run lintESLint
npm run version:patchBump patch version

License

MIT

Ver o original no GitHub

Bom para

Relacionados