--- title: Build a ChatGPT Connector (MCP server) description: Build a ChatGPT MCP server with mcp-handler and Fluid compute. Add search, fetch, and OAuth, deploy to Vercel, then validate it in developer mode. url: /kb/guide/mcp-server-chatgpt-connector canonical_url: "https://vercel.com/kb/guide/mcp-server-chatgpt-connector" published: 2025-11-03 last_updated: 2026-08-18 authors: Vercel related: - /docs/fluid-compute - /docs/functions/usage-and-pricing - /docs/instant-rollback - /docs/deployment-protection - /docs/vercel-firewall - /docs/agent-resources/vercel-mcp - /docs/workflows - /docs/mcp/deploy-mcp-servers-to-vercel - /docs/mcp - /docs/functions/configuring-functions/duration - /kb/guide/mcp-server-with-weather-tool-express install_vercel_plugin: npx plugins add vercel/vercel-plugin --- ## Related pages > **For AI agents:** Follow these links to understand how this page connects to the rest of the Vercel ecosystem. For the full cross-link map (inbound, outbound, prerequisites, and semantic neighbors), see the .graph.md link below. - [Building efficient MCP servers](https://vercel.com/blog/building-efficient-mcp-servers?from=related&source_path=%2Fkb%2Fguide%2Fmcp-server-chatgpt-connector&source_site=vercel-kb&relationship=related) - [Introducing Vercel MCP: Connect Vercel to your AI tools](https://vercel.com/blog/introducing-vercel-mcp-connect-vercel-to-your-ai-tools?from=related&source_path=%2Fkb%2Fguide%2Fmcp-server-chatgpt-connector&source_site=vercel-kb&relationship=related) - [MCP Connections](https://eve.dev/docs/connections/mcp?from=related&source_path=%2Fkb%2Fguide%2Fmcp-server-chatgpt-connector&source_site=vercel-kb&relationship=related) — Connect an eve agent to a remote MCP server, authorize it with Vercel Connect or static credentials, and control which t - [MCP server support on Vercel](https://vercel.com/changelog/mcp-server-support-on-vercel?from=related&source_path=%2Fkb%2Fguide%2Fmcp-server-chatgpt-connector&source_site=vercel-kb&relationship=related) - [Model Context Protocol (MCP) explained: An FAQ](https://vercel.com/blog/model-context-protocol-mcp-explained?from=related&source_path=%2Fkb%2Fguide%2Fmcp-server-chatgpt-connector&source_site=vercel-kb&relationship=related) - [Model Context Protocol (MCP)](https://ai-sdk.dev/docs/ai-sdk-core/mcp-tools?from=related&source_path=%2Fkb%2Fguide%2Fmcp-server-chatgpt-connector&source_site=vercel-kb&relationship=related) - [How to build an MCP server with Nuxt](https://vercel.com/kb/guide/how-to-build-an-mcp-server-with-nuxt?from=related&source_path=%2Fkb%2Fguide%2Fmcp-server-chatgpt-connector&source_site=vercel-kb&relationship=related) — Add an MCP server to your Nuxt app with the Nuxt MCP Toolkit. Create tools, resources, and prompt templates that AI assi - [Using xmcp with Next.js](https://vercel.com/kb/guide/using-xmcp-with-nextjs?from=related&source_path=%2Fkb%2Fguide%2Fmcp-server-chatgpt-connector&source_site=vercel-kb&relationship=related) — Add an MCP server to an existing Next.js app with xmcp. Create typed tools, add authentication, and deploy to Vercel as - [How to create a contentful asset on Vercel](https://vercel.com/kb/guide/how-to-create-a-contentful-asset-on-vercel?from=related&source_path=%2Fkb%2Fguide%2Fmcp-server-chatgpt-connector&source_site=vercel-kb&relationship=related) — This is my wonderful - [Application authentication on Vercel](https://vercel.com/kb/guide/application-authentication-on-vercel?from=related&source_path=%2Fkb%2Fguide%2Fmcp-server-chatgpt-connector&source_site=vercel-kb&relationship=related) — Secure application authentication on Vercel across layers: proxy checks, the Data Access Layer, PPR-safe rendering, and - [Add MCP Apps to your AI SDK application](https://vercel.com/kb/guide/ai-sdk-mcp-apps?from=related&source_path=%2Fkb%2Fguide%2Fmcp-server-chatgpt-connector&source_site=vercel-kb&relationship=related) — Build an MCP Apps host with the AI SDK using @ai-sdk/mcp and @ai-sdk/react to filter model-visible tools, read ui:// res Full cross-link map for this page: [/kb/guide/mcp-server-chatgpt-connector.graph.md](/kb/guide/mcp-server-chatgpt-connector.graph.md?from=related&source_path=%2Fkb%2Fguide%2Fmcp-server-chatgpt-connector&source_site=vercel-kb&relationship=graph) A ChatGPT connector is a remote MCP server that ChatGPT reaches over HTTPS. Model Context Protocol (MCP) is the open standard that describes those calls, so once the connector is added, ChatGPT can invoke your tools and read your data inside a conversation. This guide covers the whole path, from the packages you need through the route handler, authorization, deployment, and the validation flow in ChatGPT. It uses [the mcp-handler package](https://github.com/vercel/mcp-handler), Vercel's framework-agnostic HTTP adapter for MCP servers. ## What you need to build a ChatGPT MCP server Five things have to be in place before the connector will add: - **A Vercel project:** Next.js works out of the box, as does any framework that exposes Web-standard `Request` and `Response`, including Nuxt, SvelteKit, and Hono. - **Node.js 20 or later:** Earlier versions won't run `mcp-handler` 2.x, which is the release this guide uses throughout. - **The MCP packages:** `mcp-handler` 2.x pairs with `@modelcontextprotocol/server` v2 and `zod` 4, and the three versions have to move together. - **A ChatGPT account with developer mode:** You add and test the connector there, and availability depends on your account and workspace policy. - **An OAuth authorization server:** Only needed if your tools read private data on behalf of a signed-in user. If you'd rather start from working code, the [MCP server template](https://vercel.com/templates/next.js/model-context-protocol-mcp-with-next-js) and the [ChatGPT app template](https://vercel.com/templates/next.js/chatgpt-app-with-next-js) are both ready to deploy. ## How ChatGPT connects to a remote MCP server ChatGPT is a remote client, so it never launches your server as a subprocess the way a local editor does. It sends HTTP requests to a public HTTPS endpoint that speaks Streamable HTTP, conventionally at `/mcp`. If the server runs on a private network or a laptop, use [Secure MCP Tunnel](https://developers.openai.com/api/docs/guides/secure-mcp-tunnels) rather than exposing it. At connection time, ChatGPT reads the tool names, descriptions, schemas, and annotations that your server advertises, then decides which tool to call based on a user's prompt. It captures that metadata once, when you create the connection, which matters later when you switch tools. The [2026-07-28 MCP specification](https://modelcontextprotocol.io/specification/2026-07-28/changelog) removes protocol-level sessions and the `initialize` handshake, so every request now carries its own protocol version and capabilities and can land on any instance. The specification also adds `Mcp-Method` and `Mcp-Name` headers, so a load balancer can route without parsing the request body. Statelessness lines up with how Vercel Functions already work. `mcp-handler` 2.x serves the 2026-07-28 specification natively and falls back to stateless Streamable HTTP for 2025-era clients from the same handler, so a single route covers both generations. The older HTTP+SSE transport, which held a connection open with Server-Sent Events (SSE), is removed in 2.x, and Redis is no longer a dependency. ## How to deploy an MCP server for ChatGPT on Vercel Four steps take you from an empty route to a deployed endpoint. ### 1\. Install the packages Add the adapter, the SDK server package, and Zod: ```bash npm install mcp-handler @modelcontextprotocol/server zod ``` Version 2.x depends on `@modelcontextprotocol/server`, which is the SDK v2 package installed above. The older 1.x line depends on `@modelcontextprotocol/sdk` instead, where releases before 1.26.0 carry a known security vulnerability, so pin 1.26.0 or later if you stay on 1.x. ### **2\. Create the route handler** `createMcpHandler` returns a Web-standard request handler. Mount it in a Next.js route and export it for both methods: ```tsx import { createMcpHandler } from "mcp-handler"; import { z } from "zod"; const handler = createMcpHandler((server) => { server.registerTool( "roll_dice", { title: "Roll Dice", description: "Roll a dice with a specified number of sides.", inputSchema: z.object({ sides: z.number().int().min(2), }), }, async ({ sides }) => { const value = 1 + Math.floor(Math.random() * sides); return { content: [{ type: "text", text: `You rolled a ${value}.` }], }; }, ); }); export { handler as GET, handler as POST }; ``` The `/api/mcp` path is a convention rather than a requirement. `mcp-handler` doesn't inspect the pathname, so you can mount the handler on any route and give clients that route's full URL. ### 3\. Test the server locally Run MCP Inspector against your dev server before ChatGPT ever sees it: ```bash npx @modelcontextprotocol/inspector@latest ``` In the inspector, select **Streamable HTTP**, enter `http://localhost:3000/api/mcp`, then click **Connect** and **List Tools**. Exercise each tool with real inputs, missing identifiers, and empty results so schema and error handling are settled early. ### 4\. Deploy to Vercel Push to Git or deploy with the Vercel CLI: ```bash npx vercel deploy --prod ``` Your server is now reachable at the deployment URL plus the route, such as `https://my-mcp-server.vercel.app/api/mcp`. Keep that full URL, including the path, for the connection step. ## Why Fluid compute fits MCP server traffic That endpoint is already running on [Fluid compute](https://vercel.com/docs/fluid-compute), which is enabled by default for projects created after April 23, 2025\\. An MCP server spends most of its life idle, then handles short bursts of messages while waiting on databases and model APIs, which is the traffic shape it's built for. Instead of one isolated instance per invocation, multiple invocations share the same instance. In-memory state and open connections survive between requests, and existing capacity absorbs new connections before Vercel scales out. Billing follows the same idea. You pay $0.128 per hour of Active CPU and $0.0106 per GB-hour of Provisioned Memory in the default region. CPU accrues only while your code runs, memory accrues while a request is in flight, and nothing accrues between requests. Regional rates differ, so check [Functions pricing](https://vercel.com/docs/functions/usage-and-pricing) for the region you deploy to. Deploying the connector on Vercel brings the rest of the platform with it: - **Instant Rollback:** Use an [instant rollback](https://vercel.com/docs/instant-rollback) to revert to a previous production deployment if a tool change breaks a client. - **Preview deployments:** Point ChatGPT at a preview URL to test tool changes before production, with [Deployment Protection](https://vercel.com/docs/deployment-protection) keeping it private. - **Vercel Firewall:** Apply [multi-layered protection](https://vercel.com/docs/vercel-firewall) to an endpoint that is public by necessity. - **Rolling Releases:** Roll a new version out to a fraction of traffic before promoting it. Vercel runs its own MCP server on this stack, and you can [connect ChatGPT to Vercel](https://vercel.com/docs/agent-resources/vercel-mcp) to manage projects and deployments from a conversation. With the server running, the remaining work is the tools it exposes. ## How to add search and fetch to a ChatGPT MCP server A connector no longer [requires either tool](https://platform.openai.com/docs/mcp) to be added, but deep research and company knowledge both retrieve through that read-only pair, so ship both if either surface matters to you. The `search` tool takes a query string and returns result objects carrying `id`, `title`, and `url`. The `fetch` tool takes one of those identifiers and returns the full document. Return the same value twice, as `structuredContent` and as a JSON-encoded string in the `content` array: ```tsx server.registerTool( "search", { title: "Search", description: "Search documents and return matching results.", inputSchema: z.object({ query: z.string() }), }, async ({ query }) => { const results = await searchDocuments(query); return { structuredContent: { results }, content: [{ type: "text", text: JSON.stringify({ results }) }], }; }, ); ``` The [deep research template](https://vercel.com/templates/next.js/openai-deep-research-compatible-mcp-with-next-js) implements both tools end to end against a vector store. ## How to add OAuth authorization to your MCP server Tools that read private data need a signed-in user, and MCP's HTTP layer handles that with OAuth 2.1 semantics. `mcp-handler` covers the resource-server side, so you verify tokens and point clients at your authorization server instead of implementing the specification yourself. Wrap the handler with `withMcpAuth` and supply a token verifier: ```tsx import { createMcpHandler, withMcpAuth } from "mcp-handler"; const handler = createMcpHandler(/* tool registration from the route handler step */); const verifyToken = async (req: Request, bearerToken?: string) => { if (!bearerToken) return undefined; // Replace with a call to your authorization server. const isValid = bearerToken === "your_access_token_here"; if (!isValid) return undefined; return { token: bearerToken, scopes: ["read:stuff"], clientId: "your_client_id_here", }; }; const authHandler = withMcpAuth(handler, verifyToken, { required: true, requiredScopes: ["read:stuff"], resourceMetadataPath: "/.well-known/oauth-protected-resource", }); export { authHandler as GET, authHandler as POST }; ``` Unauthenticated requests now get a 401 with a challenge that points at your protected resource metadata, which the client reads to find your authorization server. Serve that document from a second route: ```tsx import { protectedResourceHandler, metadataCorsOptionsRequestHandler, } from "mcp-handler"; const handler = protectedResourceHandler({ authServerUrls: [""], }); const corsHandler = metadataCorsOptionsRequestHandler(); export { handler as GET, corsHandler as OPTIONS }; ``` The 2026-07-28 specification deprecates Dynamic Client Registration in favor of Client ID Metadata Documents, where a client identifies itself with an HTTPS URL that serves its own metadata. Your authorization server advertises and implements that support, not your MCP server. Check whether your provider offers it before you build around registration. The [authorization guide](https://github.com/vercel/mcp-handler/blob/main/docs/AUTHORIZATION.md) has the full wiring. ## How to connect and test your ChatGPT connector With the server deployed, ChatGPT's own connection flow doubles as your validation harness. Turn on developer mode first: 1. Open **Settings**. 2. Select **Security and login**. 3. Turn on **Developer mode**. Availability depends on your account and workspace policy, so the toggle may be absent on some plans. Then add the server: 1. Go to ChatGPT Plugins. 2. Select the plus button. 3. Enter a user-facing name and description. 4. Under **Connection**, enter your MCP server URL, including the `/mcp` path. 5. Create the connection. 6. Review the tools and metadata discovered from the server. If the tools you expect appear in that list, transport and tool discovery both work. Start a new conversation and add the connection from the tools menu. Run prompts that should call a specific tool alongside prompts that shouldn't call anything, so you catch over-eager tool selection early. ## How to troubleshoot a ChatGPT connector that fails Most failures here are silent. The connector doesn't add, or a tool stops appearing, with no error text to work from. Work through these causes in order: - **ChatGPT can't reach the server:** The endpoint has to be public HTTPS, and the URL has to include the route path. Confirm the same URL works in MCP Inspector, or use Secure MCP Tunnel for a private server. - **Updated tools don't appear:** Metadata is captured when the connection is created. Deploy the change, open the connection in ChatGPT Plugins, select **Refresh**, then start a new conversation. - **The build breaks after upgrading to 2.x:** `server.tool()` is now `registerTool`, `inputSchema` takes a full schema such as `z.object({ ... })` instead of a raw Zod shape, and `basePath`, `disableSse`, `redisUrl`, `maxDuration`, and `sessionIdGenerator` are gone. Mount the handler at the route you want, rather than configuring paths. - **Older SSE clients drop off:** The HTTP+SSE transport from 2024-11-05 is removed in 2.x. Stay on `mcp-handler` 1.x until those clients migrate. - **The function times out while streaming:** A streaming response can keep a function open with no work being done. Set `maxDuration` per function and send data during real work instead of going silent. - **OAuth fails partway through sign-in:** A person needs time to finish a browser flow. Confirm `/.well-known/oauth-protected-resource` resolves in production and lists the correct authorization server. Set the duration ceiling explicitly rather than inheriting the default. On Pro and Enterprise, raise it on the MCP route alone: ```json { "$schema": "", "functions": { "app/api/mcp/route.ts": { "maxDuration": 800 } } } ``` With Fluid compute, every plan defaults to 300 seconds. Hobby is capped there, so the setting above has no effect on a Hobby project. Values above 800 seconds are in beta and need per-function configuration on supported Node.js and Python versions. If a connection needs to pause and resume across minutes or months, [Vercel Workflows](https://vercel.com/docs/workflows) is the better fit than a longer ceiling. ## Next steps Once the connector validates in ChatGPT, the same server works with any MCP client that speaks Streamable HTTP. [Start a new Vercel project](https://vercel.com/new) for your server, or [browse the templates](https://vercel.com/templates) to begin from a working MCP implementation. ## Related resources - [Deploy MCP servers to Vercel](https://vercel.com/docs/mcp/deploy-mcp-servers-to-vercel) - [MCP on Vercel](https://vercel.com/docs/mcp) - [Fluid compute](https://vercel.com/docs/fluid-compute) - [Configuring function duration](https://vercel.com/docs/functions/configuring-functions/duration) - [Vercel MCP server](https://vercel.com/docs/agent-resources/vercel-mcp) - [Build an MCP server with Express](https://vercel.com/kb/guide/mcp-server-with-weather-tool-express) ## Frequently asked questions ### Do I need search-and-fetch tools for a ChatGPT connector? No, not anymore. Neither tool is required to add a connector, so a server without them still works in chat. It stays inert in deep research and company knowledge, which retrieve only through that pair. If you want those surfaces, name the tools exactly `search` and `fetch` and keep both read-only. ### Does my MCP server need to be public for ChatGPT to use it? Yes for a normal connection, and again at submission. ChatGPT connects to remote servers via a public HTTPS endpoint, so it can't connect to a laptop or a private network. Secure MCP Tunnel covers private servers during development, but it doesn't replace the public endpoint required for plugin submission. ### Why doesn't my ChatGPT connector show my updated tools? Metadata is captured when the connection is created, so a redeploy alone changes nothing. Open the connection in ChatGPT Plugins and select **Refresh**. Published plugins behave differently, running on reviewed metadata snapshots, so updating those means scanning the server, submitting a new version, and publishing the approved one. ### Do I still need Redis to run an MCP server on Vercel? No. `mcp-handler` 2.x dropped the transport that needed shared session state, and the 2026-07-28 specification removed protocol-level sessions. State that has to survive across calls now lives in your application, as a handle your tool mints and returns for the model to pass back as an ordinary argument. ### What is the maximum function duration for a streaming MCP server? With Fluid compute, every plan defaults to 300 seconds. Hobby is capped there, while Pro and Enterprise reach 800 seconds, and values above that are in beta and set per function. A function that runs past its ceiling returns a 504 with `FUNCTION_INVOCATION_TIMEOUT`. For longer pauses, use Vercel Workflows.