Builds remote MCP (Model Context Protocol) servers on Cloudflare Workers with tools, OAuth authentication, and production deployment. Generates server code, configures auth providers, and deploys to Workers. Use when: user wants to "build MCP server", "create MCP tools", "remote MCP", "deploy MCP", add "OAuth to MCP", or mentions Model Context Protocol on Cloudflare. Also triggers on "MCP authentication" or "MCP deployment". Biases towards retrieval from Cloudflare docs over pre-trained knowledge.
80
100%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Passed
No findings from the security scan
Your knowledge of the MCP SDK and Cloudflare Workers integration may be outdated. Prefer retrieval over pre-training for any MCP server task.
| Source | How to retrieve | Use for |
|---|---|---|
| MCP docs | https://developers.cloudflare.com/agents/mcp/ | Server setup, auth, deployment |
| MCP spec | https://modelcontextprotocol.io/ | Protocol spec, tool/resource definitions |
| Workers docs | Search tool or https://developers.cloudflare.com/workers/ | Runtime APIs, bindings, config |
npm install -g wrangler)npm create cloudflare@latest -- my-mcp-server \
--template=cloudflare/ai/demos/remote-mcp-authless
cd my-mcp-server
npm startServer runs at http://localhost:8788/mcp
npm create cloudflare@latest -- my-mcp-server \
--template=cloudflare/ai/demos/remote-mcp-github-oauth
cd my-mcp-serverRequires OAuth app setup. See references/oauth-setup.md.
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) }],
};
}
);
}
}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.
# Start server
npm start
# In another terminal, test with MCP Inspector
npx @modelcontextprotocol/inspector@latest
# Open http://localhost:5173, enter http://localhost:8788/mcpnpx wrangler deployServer accessible at https://[worker-name].[account].workers.dev/mcp
Codex MCP client setup:
codex mcp add my-server -- npx mcp-remote https://my-mcp.workers.dev/mcpRestart Codex after updating the MCP configuration.
// 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) },
],
};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
}
);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) }] };
});
}
}For OAuth-protected servers, see references/oauth-setup.md.
Supported providers:
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"init() registers tools before connectionswrangler tail/mcpwrangler deployments listGITHUB_CLIENT_ID and GITHUB_CLIENT_SECRET are sethttp://localhost:8788/callback11c74d6
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.