Adding a remote MCP server to a Next.js app, OAuth and all

A developer shipped a remote MCP server for Deoochform, a form builder that lets users create forms by prompting an assistant, built on Next.js 16's App Router with the official Model Context Protocol SDK. The implementation covers the full OAuth discovery chain — protected-resource and authorization-server metadata endpoints plus /authorize, /token, and /register — so clients like Claude and ChatGPT can connect over HTTPS with a browser sign-in instead of a pasted API key. The developer notes the server is constructed per request with the caller's identity baked in, and that stateless operation is required on serverless hosts like Vercel.

Most "add MCP to your app" posts stop at stdio: a local process, a config file, a token you paste in. That works on your laptop and nowhere else. A remote MCP server, the kind Claude or ChatGPT connects to over HTTPS with a browser sign-in, needs OAuth, and the interesting parts are the ones no tutorial covers. I shipped one for Deoochform https://deoochform.com , a form builder where the whole point is that you can build the form by asking an assistant instead of dragging fields around. So the MCP server is not a side feature, it is the product surface. That forced me to get the auth story right rather than hand-waving it with a pasted API key. Here is the whole thing, Next.js 16 App Router, no framework beyond the official SDK. Four HTTP surfaces: POST /api/mcp : the MCP endpoint itself. GET /.well-known/oauth-protected-resource/api/mcp : "here is who authorizes me". GET /.well-known/oauth-authorization-server : "here are my OAuth endpoints". /authorize , /token , /register : the OAuth endpoints themselves. A client that has never seen your server walks all four in order, unprompted. That discovery chain is the whole reason a user can type a URL into Claude and get a browser sign-in instead of a token prompt. The SDK ships a transport that speaks Web-standard Request / Response , which is exactly what an App Router route handler deals in: js import { WebStandardStreamableHTTPServerTransport } from "@modelcontextprotocol/sdk/server/webStandardStreamableHttp.js"; async function handle request: Request { const actor = await resolveActor request ; if actor return unauthorized request ; const server = createMcpServer actor ; const transport = new WebStandardStreamableHTTPServerTransport { sessionIdGenerator: undefined, enableJsonResponse: true, } ; await server.connect transport ; return transport.handleRequest request ; } export { handle as GET, handle as POST, handle as DELETE }; Two things worth pausing on. sessionIdGenerator: undefined makes the server stateless. On Vercel or any serverless host, consecutive requests land on different instances, so there is nowhere for a session to live. Stateless is not a downgrade here, it is the only thing that works. The server is constructed per request, with the actor baked in . Not a module-level singleton with the user passed into each tool call. Every tool closes over the caller's identity, so there is no code path where a tool can read a row belonging to somebody else. It costs one object allocation per request and removes an entire category of bug. Browser-based clients ChatGPT, Claude on the web call your endpoint cross-origin. The browser fires a preflight OPTIONS first, and if that fails the real request never happens. You see nothing in your logs, and the client says something unhelpful about being unable to connect. js const CORS HEADERS = { "Access-Control-Allow-Origin": " ", "Access-Control-Allow-Methods": "GET, POST, DELETE, OPTIONS", "Access-Control-Allow-Headers": "Content-Type, Authorization, mcp-session-id, mcp-protocol-version, Last-Event-ID", "Access-Control-Expose-Headers": "mcp-session-id, mcp-protocol-version", }; Expose-Headers is the one people miss. Without it the browser hides the MCP protocol headers from the client even though your server sent them. An unauthenticated call must not just return 401. It has to say where to go, using WWW-Authenticate per RFC 9728: js const metadataUrl = ${origin}/.well-known/oauth-protected-resource/api/mcp ; return Response.json { error: "Unauthorized" }, { status: 401, headers: { "WWW-Authenticate": Bearer resource metadata="${metadataUrl}" }, }, ; This single header is the trigger for the entire browser sign-in flow. Return a bare 401 and the client concludes your server is broken rather than password-protected. Note the metadata path: RFC 9728 nests it under the resource's own path. If you serve two MCP endpoints, /api/mcp and /api/mcp/v2 , each needs its own document at its own nested path. They are not interchangeable. // /.well-known/oauth-protected-resource/api/mcp/route.ts export async function GET { return NextResponse.json { resource: ${origin}/api/mcp , authorization servers: origin , } ; } You are probably already sitting on a session system. You do not need Auth0 for this. The metadata document is a static JSON file plus three routes: export async function GET { return NextResponse.json { issuer: origin, authorization endpoint: ${origin}/authorize , token endpoint: ${origin}/token , registration endpoint: ${origin}/register , response types supported: "code" , grant types supported: "authorization code" , code challenge methods supported: "S256" , token endpoint auth methods supported: "none" , } ; } token endpoint auth method: "none" is correct and not a shortcut. An MCP connector is a public client. It ships to end users and cannot keep a secret, so PKCE, not a client secret, is what proves the token exchange came from the same client that started the flow. If you also serve confidential clients, say a Zapier integration, add client secret basic and client secret post alongside it. RFC 7591 says a client can register itself. In practice, for a public client authenticated by PKCE, there is nothing meaningful to store: js export async function POST request: Request { const body = await request.json .catch = {} ; return NextResponse.json { client id: "dfc " + randomBytes 9 .toString "base64url" , client name: body.client name ?? "MCP Client", redirect uris: body.redirect uris ?? , grant types: "authorization code" , response types: "code" , token endpoint auth method: "none", } ; } That is the entire endpoint. It mints an id and hands it back. A clients table would be ceremony: nothing downstream consults it. But be careful about what you conclude from that. "We do not register clients, PKCE covers it" is the sentence I would have written before I thought it through, and it is wrong. See the next section. PKCE binds an authorization code to whoever started the flow. The usual mental model is that this makes an unregistered redirect uri safe, because a stolen code is useless without the verifier. That model breaks when the attacker is the one who started the flow . They craft an /authorize link with their own redirect uri and their own code challenge , and send it to a signed-in victim. The victim's browser follows it. The code is minted against the victim's session, redirects to the attacker's callback, and the attacker exchanges it with the verifier they chose. An access token for someone else's account, from one click. PKCE did its job perfectly and protected nobody, because the attacker held the verifier all along. So the redirect cannot be automatic. GET /authorize renders a consent page instead, and the code is only minted by a POST from that page: js export async function POST request: Request { const origin = request.headers.get "origin" ; if origin == url.origin { return NextResponse.json { error: "invalid request", error description: "Cross-origin approval refused." }, { status: 403 }, ; } // ... re-read params, re-read the session, then mint } Two properties do the work. The approval is a step a crafted link cannot perform on the victim's behalf. And Origin is sent on every form POST and cannot be forged by page script, so a cross-site auto-submitting form is not an approval either. The consent page names the host the code is about to go to, not the full URI. The host is the part that actually matters to the decision, and a long URI just gives someone something to skim past. Re-read the session inside the POST rather than trusting a hidden field. The session is the only thing that says whose account the code is for. One caveat on the redirect itself: use a 303 , not a 307. Approval arrives as a POST, and 307 preserves the method, so the browser would POST the code to a callback that only answers GET. The client reports a bare "Bad Request" and it looks like the client's bug rather than yours. A confidential client with a pre-registered redirect uri a Zapier integration, say can skip the prompt. There is no third party to consent to, because the caller could not have changed the destination. Twelve lines, all of it standard library: js import { randomBytes, createHash } from "crypto"; const CODE TTL MS = 5 60 1000; export const generateAuthCode = = "dfc " + randomBytes 24 .toString "base64url" ; export const codeExpiry = = new Date Date.now + CODE TTL MS .toISOString ; export function verifyPkce verifier: string, challenge: string { return createHash "sha256" .update verifier .digest "base64url" === challenge; } Five-minute code TTL, single use, deleted on exchange. /authorize runs behind your normal session check, so an unauthenticated user hits your existing login first and comes back. That is the whole reason the user never sees a token. If you also compare client secrets anywhere, use timingSafeEqual , and check lengths yourself first. timingSafeEqual throws on a length mismatch, and an uncaught throw becomes a 500 that leaks the secret's length. The token you issue can just be a row. Store a hash, never the token: const { data: token } = await admin .from "api tokens" .select "id, user id, revoked at, profiles id, email, role, plan " .eq "token hash", hashToken raw .is "revoked at", null .maybeSingle ; One query gets you validity and the caller's identity, role, and plan. The connection then acts as that user, with their permissions, which means your existing row-level security applies to MCP traffic for free. No parallel permission model to keep in sync. I originally planned one endpoint with a capability flag, so a listed directory connector could be restricted while my own stayed full-featured. It does not work: an app directory registers its OAuth client against a base URL and then freezes it. Whatever a listed URL is allowed to do has to be settled before you list it. So there are two endpoints, /api/mcp and /api/mcp/v2 , same server behind different options. The public one cannot see or create payment fields at all, which means nothing built through the directory listing can collect money. Two routes, five lines each: export const { GET, POST, DELETE, OPTIONS } = mcpHandlers { path: "/api/mcp/v2", payments: false } ; Capability decisions are URL-shaped, not runtime-shaped. Plan for that before you submit anywhere. sessionIdGenerator: undefined . Expose-Headers . WWW-Authenticate with the resource metadata URL. None of this is much code. It is roughly 150 lines across six files. The hard part was working out which pieces of the OAuth spec actually apply to a public client that a user connects by pasting a URL, and which are ceremony. The result is what I wanted: you paste https://deoochform.com/api/mcp/v2 into Claude, a browser tab opens, you sign in, and you are done. No token to copy, nothing to store. The MCP server docs https://deoochform.com/docs/mcp-server shows it from the user side if you want to see what the flow feels like before building your own.