megachangelog
Feature1.0

Workers OAuth Provider v1: Split API and MCP 2026-07-28 Support

Workers OAuth Provider reaches v1 with a new split API architecture that separates authorization servers from resource servers, enabling MCP servers to run independently while validating tokens over Service Bindings. The library now supports the MCP 2026-07-28 specification including Client ID Metadata Documents and issuer identification, with step-up authorization via insufficientScope() and backwards compatibility for older clients.

@cloudflare/workers-oauth-provider ↗︎ is now v1, with a new split API. One Worker acts as the authorization server: it signs users in and issues tokens. Your MCP server acts as the resource server, and can run in another Worker. It validates each token with the authorization server over a Service Binding, without crossing the public Internet.

The split API

import {
	OAuthAuthorizationServer,
	OAuthResourceServer,
	insufficientScope,
} from "@cloudflare/workers-oauth-provider";
import { WorkerEntrypoint } from "cloudflare:workers";

// auth-server Worker: signs users in and issues tokens for both MCP servers.
const authorizationServer = new OAuthAuthorizationServer({
	issuer: "https://auth.example.com",
	resources: [
		"https://calendar.example.com/mcp",
		"https://drive.example.com/mcp",
	],
	scopesSupported: ["calendar:read", "calendar:write", "offline_access"],
	clientIdMetadataDocumentEnabled: true,
});

export class AuthServer extends WorkerEntrypoint {
	fetch(request) {
		if (new URL(request.url).pathname === "/authorize") {
			return showConsent(request, this.env);
		}
		return authorizationServer.fetch(request, this.env, this.ctx);
	}

	validateToken(resource, token) {
		return authorizationServer.validateToken(resource, token, this.env);
	}
}

// calendar MCP Worker: checks tokens with AuthServer over a Service Binding.
export const calendar = new OAuthResourceServer({
	resourceMetadata: {
		resource: "https://calendar.example.com/mcp",
		authorization_servers: ["https://auth.example.com"],
	},
	requiredScopes: ["calendar:read"],
	validateToken: (env) => env.AUTH_SERVER.validateToken,
	handler: {
		fetch(request, env, ctx) {
			if (
				request.method === "POST" &&
				!ctx.auth.scope.includes("calendar:write")
			) {
				return insufficientScope(ctx.auth, ["calendar:read", "calendar:write"]);
			}
			return handleMcp(request, ctx.props);
		},
	},
});
import {
	OAuthAuthorizationServer,
	OAuthResourceServer,
	insufficientScope,
} from "@cloudflare/workers-oauth-provider";
import { WorkerEntrypoint } from "cloudflare:workers";

// auth-server Worker: signs users in and issues tokens for both MCP servers.
const authorizationServer = new OAuthAuthorizationServer<Env>({
	issuer: "https://auth.example.com",
	resources: [
		"https://calendar.example.com/mcp",
		"https://drive.example.com/mcp",
	],
	scopesSupported: ["calendar:read", "calendar:write", "offline_access"],
	clientIdMetadataDocumentEnabled: true,
});

export class AuthServer extends WorkerEntrypoint<Env> {
	fetch(request: Request) {
		if (new URL(request.url).pathname === "/authorize") {
			return showConsent(request, this.env);
		}
		return authorizationServer.fetch(request, this.env, this.ctx);
	}

	validateToken(resource: string, token: string) {
		return authorizationServer.validateToken(resource, token, this.env);
	}
}

// calendar MCP Worker: checks tokens with AuthServer over a Service Binding.
export const calendar = new OAuthResourceServer<Env, AuthProps>({
	resourceMetadata: {
		resource: "https://calendar.example.com/mcp",
		authorization_servers: ["https://auth.example.com"],
	},
	requiredScopes: ["calendar:read"],
	validateToken: (env) => env.AUTH_SERVER.validateToken,
	handler: {
		fetch(request, env, ctx) {
			if (
				request.method === "POST" &&
				!ctx.auth.scope.includes("calendar:write")
			) {
				return insufficientScope(ctx.auth, ["calendar:read", "calendar:write"]);
			}
			return handleMcp(request, ctx.props);
		},
	},
});

In the example, env.AUTH_SERVER.validateToken is that Service Binding call. The calendar Worker needs no KV namespace of its own.

{
	"name": "calendar-mcp",
	"main": "src/index.ts",
	// Set this to today's date
	"compatibility_date": "2026-10-01",
	"services": [
		{
			"binding": "AUTH_SERVER",
			"service": "auth-server",
			"entrypoint": "AuthServer",
		},
	],
}
name = "calendar-mcp"
main = "src/index.ts"
# Set this to today's date
compatibility_date = "2026-10-01"

[[services]]
binding = "AUTH_SERVER"
service = "auth-server"
entrypoint = "AuthServer"

OAuthResourceServer publishes the RFC 9728 ↗︎ protected resource metadata that MCP clients use to find your authorization server. It answers requests without a token with a 401 challenge that points to that metadata. It also rejects tokens issued for any other resource.

You can still use OAuthProvider as both the authorization server and the MCP server. For most 0.x deployments, the only required change is to add resourceMetadata: { resource }.

Other updates and helpers

Upgrade with the migration skill

npmyarnpnpmbun
npm i @cloudflare/workers-oauth-provider@latest
yarn add @cloudflare/workers-oauth-provider@latest
pnpm add @cloudflare/workers-oauth-provider@latest
bun add @cloudflare/workers-oauth-provider@latest

Point your coding agent at node_modules/@cloudflare/workers-oauth-provider/skills/migrate-to-1.0/SKILL.md, or follow the migration guide ↗︎.

For both Workers in full, refer to the split Workers example ↗︎.

workersoauthmcpauthapi

Source: original entry ↗

More from Cloudflare

Follow Cloudflare to get its new changes in your feed and email digest.

Feature

Cloudflare API MCP server now serves Cloudflare skills

The Cloudflare API MCP server now integrates with the Skills over MCP extension, allowing MCP clients to discover and access Cloudflare skills. Users can add the MCP server endpoint to compatible MCP clients to access these skills.

apimcpagentsintegrationextension
Feature

WAF failed detections field now available in Rules

A new cf.appsec.request.failed_detections field lets you control how rules handle requests when security detections fail. This array of detection IDs covers content scanning, WAF attack scoring, attack signatures, leaked credentials, and AI-based PII/prompt injection/custom topic detection failures, and works across custom rules, rate limiting rules, and request header transform rules.

wafrulessecurityapidetections
Improvement

Markdown for Agents: More efficient in-process streaming conversion

Markdown for Agents now uses an in-process streaming engine at the edge to convert HTML, reducing overhead and memory use. The conversion limit increased from 2 MiB to 6 MiB, and token count headers are no longer generated.

markdownagentsperformancestreamingapi
See all Cloudflare changes →