building-mcp-server-on-cloudflare

por openai

Construye servidores MCP (Model Context Protocol) remotos en Cloudflare Workers con herramientas, autenticación OAuth y despliegue en producción. Genera código de servidor,…

npx skills add https://github.com/openai/plugins --skill building-mcp-server-on-cloudflare

Building MCP Servers on Cloudflare

Your knowledge of the MCP SDK and Cloudflare Workers integration may be outdated. Prefer retrieval over pre-training for any MCP server task.

Retrieval Sources

SourceHow to retrieveUse for
MCP docshttps://developers.cloudflare.com/agents/mcp/Server setup, auth, deployment
MCP spechttps://modelcontextprotocol.io/Protocol spec, tool/resource definitions
Workers docsSearch tool or https://developers.cloudflare.com/workers/Runtime APIs, bindings, config

When to Use

  • User wants to build a remote MCP server
  • User needs to expose tools via MCP
  • User asks about MCP authentication or OAuth
  • User wants to deploy MCP to Cloudflare Workers

Prerequisites

  • Cloudflare account with Workers enabled
  • Node.js 18+ and npm/pnpm/yarn
  • Wrangler CLI (npm install -g wrangler)

Quick Start

Option 1: Public Server (No Auth)

npm create cloudflare@latest -- my-mcp-server \
  --template=cloudflare/ai/demos/remote-mcp-authless
cd my-mcp-server
npm start

Server runs at http://localhost:8788/mcp

Option 2: Authenticated Server (OAuth)

npm create cloudflare@latest -- my-mcp-server \
  --template=cloudflare/ai/demos/remote-mcp-github-oauth
cd my-mcp-server

Requires OAuth app setup. See references/oauth-setup.md.

Core Workflow

Step 1: Define Tools

Tools are functions MCP clients can call. Define them using server.tool():

import { McpAgent } from "agents/mcp";
import { z } from "zod";

export class MyMCP extends McpAgent {
  server = new Server({ name: "my-mcp", version: "1.0.0" });

  async init() {
    // Simple tool with parameters
    this.server.tool(
      "add",
      { a: z.number(), b: z.number() },
      async ({ a, b }) => ({
        content: [{ type: "text", text: String(a + b) }],
      })
    );

    // Tool that calls external API
    this.server.tool(
      "get_weather",
      { city: z.string() },
      async ({ city }) => {
        const response = await fetch(`https://api.weather.com/${city}`);
        const data = await response.json();
        return {
          content: [{ type: "text", text: JSON.stringify(data) }],
        };
      }
    );
  }
}

Step 2: Configure Entry Point

Public server (src/index.ts):

import { MyMCP } from "./mcp";

export default {
  fetch(request: Request, env: Env, ctx: ExecutionContext) {
    const url = new URL(request.url);
    if (url.pathname === "/mcp") {
      return MyMCP.serveSSE("/mcp").fetch(request, env, ctx);
    }
    return new Response("MCP Server", { status: 200 });
  },
};

export { MyMCP };

Authenticated server — See references/oauth-setup.md.

Step 3: Test Locally

# Start server
npm start

# In another terminal, test with MCP Inspector
npx @modelcontextprotocol/inspector@latest
# Open http://localhost:5173, enter http://localhost:8788/mcp

Step 4: Deploy

npx wrangler deploy

Server accessible at https://[worker-name].[account].workers.dev/mcp

Step 5: Connect Clients

Codex MCP client setup:

codex mcp add my-server -- npx mcp-remote https://my-mcp.workers.dev/mcp

Restart Codex after updating the MCP configuration.

Tool Patterns

Return Types

// Text response
return { content: [{ type: "text", text: "result" }] };

// Multiple content items
return {
  content: [
    { type: "text", text: "Here's the data:" },
    { type: "text", text: JSON.stringify(data, null, 2) },
  ],
};

Input Validation with Zod

this.server.tool(
  "create_user",
  {
    email: z.string().email(),
    name: z.string().min(1).max(100),
    role: z.enum(["admin", "user", "guest"]),
    age: z.number().int().min(0).optional(),
  },
  async (params) => {
    // params are fully typed and validated
  }
);

Accessing Environment/Bindings

export class MyMCP extends McpAgent<Env> {
  async init() {
    this.server.tool("query_db", { sql: z.string() }, async ({ sql }) => {
      // Access D1 binding
      const result = await this.env.DB.prepare(sql).all();
      return { content: [{ type: "text", text: JSON.stringify(result) }] };
    });
  }
}

Authentication

For OAuth-protected servers, see references/oauth-setup.md.

Supported providers:

  • GitHub
  • Google
  • Auth0
  • Stytch
  • WorkOS
  • Any OAuth 2.0 compliant provider

Wrangler Configuration

Minimal wrangler.toml:

name = "my-mcp-server"
main = "src/index.ts"
compatibility_date = "2024-12-01"

[durable_objects]
bindings = [{ name = "MCP", class_name = "MyMCP" }]

[[migrations]]
tag = "v1"
new_classes = ["MyMCP"]

With bindings (D1, KV, etc.):

[[d1_databases]]
binding = "DB"
database_name = "my-db"
database_id = "xxx"

[[kv_namespaces]]
binding = "KV"
id = "xxx"

Common Issues

"Tool not found" in Client

  1. Verify tool name matches exactly (case-sensitive)
  2. Ensure init() registers tools before connections
  3. Check server logs: wrangler tail

Connection Fails

  1. Confirm endpoint path is /mcp
  2. Check CORS if browser-based client
  3. Verify Worker is deployed: wrangler deployments list

OAuth Redirect Errors

  1. Callback URL must match OAuth app config exactly
  2. Check GITHUB_CLIENT_ID and GITHUB_CLIENT_SECRET are set
  3. For local dev, use http://localhost:8788/callback

References

Más skills de openai

release
openai
Realizar un lanzamiento de Symphony incrementando la versión confirmada, integrándola, etiquetando el commit fusionado y verificando el flujo de trabajo de lanzamiento de Burrito. Usar cuando se solicite…
signing-entitlements
openai
Inspeccionar problemas de firma, entitlements, runtime reforzado y Gatekeeper en aplicaciones de macOS. Usar cuando se solicite diagnosticar fallos de firma de código, entitlements faltantes,…
building-ai-agent-on-cloudflare
openai
Crea agentes de IA en Cloudflare usando el Agents SDK con gestión de estado, WebSockets en tiempo real, tareas programadas, integración de herramientas y chat…
epigraphdb-skill
openai
Envía solicitudes compactas a la API de EpiGraphDB para ontología, literatura, MR, genes-fármacos y evidencia de vías de soporte. Úsalo cuando un usuario desee resúmenes concisos de EpiGraphDB.
runtime-behavior-probe
openai
Planificar y ejecutar investigaciones de comportamiento en tiempo de ejecución con scripts de sonda temporales, matrices de validación, controles de estado e informes centrados en hallazgos. Usar solo cuando…
deep-security-scan
openai
Úsalo cuando el usuario solicite un escaneo de seguridad de Codex profundo, exhaustivo, de múltiples pasadas o que reduzca la varianza, en todo el repositorio o en una ruta específica. Ejecuta pasadas independientes repetidas…
define-security-policy
openai
Definir, revisar o actualizar la guía de SECURITY.md para un repositorio o componente. Úselo cuando el usuario quiera aclarar qué debe revisar Codex Security, qué está fuera de…
validation
openai
Usar cuando Codex ya está en la fase de validación de un escaneo de seguridad o el usuario solicita explícitamente determinar si uno o más posibles hallazgos de seguridad…