building-mcp-server-on-cloudflare

oleh openai

Membangun server MCP (Model Context Protocol) jarak jauh di Cloudflare Workers dengan tools, autentikasi OAuth, dan deployment produksi. Menghasilkan kode server,...

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Your knowledge of the MCP SDK and Cloudflare Workers integration may be outdated.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

Lebih banyak skill dari openai

release
openai
Buat rilis Symphony dengan menaikkan versi yang dikomit, menandainya, menandai commit yang digabung, dan memverifikasi alur kerja rilis Burrito. Gunakan saat diminta untuk…
signing-entitlements
openai
Periksa masalah penandatanganan, hak istimewa, runtime yang diperkuat, dan Gatekeeper untuk aplikasi macOS. Gunakan saat diminta untuk mendiagnosis kegagalan penandatanganan kode, hak istimewa yang hilang,…
building-ai-agent-on-cloudflare
openai
Membangun agen AI di Cloudflare menggunakan Agents SDK dengan manajemen status, WebSockets real-time, tugas terjadwal, integrasi alat, dan obrolan…
epigraphdb-skill
openai
Kirim permintaan API EpiGraphDB yang ringkas untuk ontologi, literatur, MR, gen-obat, dan bukti jalur dukungan. Gunakan saat pengguna menginginkan ringkasan EpiGraphDB yang singkat.
runtime-behavior-probe
openai
Rencanakan dan laksanakan investigasi perilaku runtime dengan skrip probe sementara, matriks validasi, kontrol status, dan laporan berbasis temuan. Gunakan hanya ketika…
deep-security-scan
openai
Gunakan saat pengguna meminta pemindaian Keamanan Codex yang mendalam, menyeluruh, multi-pass, atau mengurangi varians di seluruh repositori atau pada jalur tertentu. Jalankan secara independen dan berulang…
define-security-policy
openai
Menentukan, meninjau, atau memperbarui panduan SECURITY.md untuk repositori atau komponen. Gunakan ketika pengguna ingin memperjelas apa yang harus ditinjau oleh Codex Security, apa yang di luar…
validation
openai
Gunakan ketika Codex sudah berada dalam fase validasi pemindaian keamanan atau pengguna secara eksplisit meminta untuk menentukan apakah satu atau lebih temuan keamanan kandidat…