--- title: Build a ChatGPT Connector (MCP server) description: Create an MCP server to bring your tools and data to ChatGPT url: /kb/guide/mcp-server-chatgpt-connector canonical_url: "https://vercel.com/kb/guide/mcp-server-chatgpt-connector" published: 2025-11-03 last_updated: 2026-07-16 authors: Anthony Shew related: - /docs/mcp/vercel-mcp - /docs/deployments/environments - /docs/vercel-firewall - /docs/mcp/deploy-mcp-servers-to-vercel - /docs/agents - /docs/vercel-sandbox - /docs/botid 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. - [Vercel MCP server](https://vercel.com/docs/agent-resources/vercel-mcp?from=related) — Vercel MCP has tools available for searching docs, managing teams, projects, and deployments, and querying Web Analytics - [MCP](https://vercel.com/docs/mcp?from=related) — Learn more about MCP and how you can use it on Vercel. - [vercel mcp](https://vercel.com/docs/cli/mcp?from=related) — Set up Model Context Protocol \(MCP\) usage with a Vercel project using the vercel mcp CLI command. - [xmcp](https://vercel.com/docs/frameworks/backend/xmcp?from=related) — Build MCP-compatible backends with xmcp and deploy to Vercel. Learn the project structure, tool format, middleware, and - [Next.js MCP Server](https://nextjs.org/docs/app/guides/mcp?from=related) — Learn how to use Next.js MCP support to allow coding agents access to your application state - [MCP Connections](https://eve.dev/docs/connections/mcp?from=related) — Connect an eve agent to a remote MCP server, authorize it with Vercel Connect or static credentials, and control which t - [Getting Started](https://vercel.com/docs/getting-started-with-vercel?from=related) — Install the Vercel CLI, add the Vercel Plugin or agent skills, and deploy your first project. - [Build an MCP Server with Weather tools using Express and Vercel](https://vercel.com/kb/guide/mcp-server-with-weather-tool-express?from=related) — Make your Express weather API accessible to AI assistants through the Model Context Protocol. - [How to create a contentful asset on Vercel](https://vercel.com/kb/guide/how-to-create-a-contentful-asset-on-vercel?from=related) — This is my wonderful - [AI Agents on Vercel](https://vercel.com/kb/guide/ai-agents?from=related) — This guide provides an overview of how to build and deploy AI agents on Vercel. - [How to build an MCP server with Nuxt](https://vercel.com/kb/guide/how-to-build-an-mcp-server-with-nuxt?from=related) — Add an MCP server to your Nuxt app with the Nuxt MCP Toolkit. Create tools, resources, and prompt templates that AI assi - [Add MCP Apps to your AI SDK application](https://vercel.com/kb/guide/ai-sdk-mcp-apps?from=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) ChatGPT can now connect with MCP servers, making the data, APIs, and other tools you use every day available in your ChatGPT sessions. This guide will walk you through the steps to build and deploy an MCP server to use as a ChatGPT Connector. ## Connect your MCP server to ChatGPT 1. [Choose a template](https://vercel.com/new/clone?demo-description=Run%20an%20Model%20Context%20Protocol%20\(MCP\)%20server%20on%20Vercel.&demo-image=%2F%2Fimages.ctfassets.net%2Fe5382hct74si%2F73N0dZEENNBHEK030NFGlR%2F643235f2fbd7c082c7333bb315fab891%2FMCP__6_.jpg&demo-title=MCP%20with%20Vercel%20Functions&demo-url=https%3A%2F%2Fmcp-on-vercel.vercel.app&from=templates&project-name=MCP%20with%20Vercel%20Functions&repository-name=model-context-protocol-mcp-with-vercel-functions&repository-url=https%3A%2F%2Fgithub.com%2Fvercel-labs%2Fmcp-on-vercel) to get started. 2. Once the deployment is created, copy the URL. Your MCP server is ready for a client to connect at the `/mcp` route. 3. Now, [follow ChatGPT’s documentation](https://platform.openai.com/docs/guides/developer-mode) to create a connector. Enable “Developer Mode” in your Advanced settings, and then add your MCP Server in the Connectors tab. Your MCP server is now available in your ChatGPT session. ## Test your MCP server 1. Start a new chat on ChatGPT. 2. Enable Developer Mode. 3. Click on “Add sources” and select your MCP server. 4. Ask ChatGPT "Use the roll\_a\_die tool to get a number" to run the tool in the MCP server. 5. On ChatGPT’s response, the tool implemented by the MCP will be called. ## What is an MCP server? MCP servers give AI models access to external capabilities. By connecting ChatGPT to an MCP server, your chat in ChatGPT quickly becomes an agent that is able to interact with the tools you use every day. For example, you can [connect ChatGPT to Vercel](https://vercel.com/docs/mcp/vercel-mcp#chatgpt) using Vercel’s own MCP server. Once authenticated, ChatGPT can interact with your projects, deployments, and fetch documentation to help you build software. ## Benefits of deploying your MCP server to Vercel **Optimized cost**: [Fluid compute](https://vercel.com/fluid) intelligently re-uses existing resources. This means Vercel Functions can be billed at Active CPU pricing, so you only pay for the compute you use. MCP servers benefit from this model due to their long idle times and quick message bursts. **Deployment previews**: [Preview deployments](https://vercel.com/docs/deployments/environments#preview-environment-pre-production) allow you to test out your changes before going live. To try out your MCP server, you can simply change the URL in ChatGPT and try them out. **Instant Rollbacks**: If you deploy to production and don’t like the results, you’re able to roll back to a previous version of your MCP server in milliseconds. This is great for recovering from bugs, breaking changes, or unintended changes to your product. **Secure by default**: [Vercel Firewall](https://vercel.com/docs/vercel-firewall) is a best-in-class, multi-layered protection layer with a platform-wide firewall to automatically protect from abnormal traffic, like DDoS attacks, and web application firewall to define custom rules for your specific needs. ## Ship more in the AI Cloud Vercel is the unified platform for AI workloads. Whether you're shipping [an MCP server](https://vercel.com/docs/mcp/deploy-mcp-servers-to-vercel), [agents](https://vercel.com/docs/agents), [running generated code](https://vercel.com/docs/vercel-sandbox), or [analyzing bot traffic to your existing application](https://vercel.com/docs/botid), we're here to help.