Model Context Protocol

Model Context Protocol (MCP) is a standard interface that lets large language models (LLMs) communicate with external tools and data sources. It allows developers and tool providers to integrate once and interoperate with any MCP-compatible system.

Connecting LLMs to external systems

LLMs don’t have access to real-time or external data by default. To provide relevant context—such as current financial data, pricing, or user-specific data—developers must connect LLMs to external systems.

Each tool or service has its own API, schema, and authentication. Managing these differences becomes difficult and error-prone as the number of integrations grows.

Standardizing LLM interaction with MCP

MCP standardizes the way LLMs interact with tools and data sources. Developers implement a single integration with MCP, and use it to manage communication with any compatible service.

Tool and data providers only need to expose an MCP interface once. After that, their system can be accessed by any MCP-enabled application.

MCP is like the USB-C standard: instead of needing different connectors for every device, you use one port to handle many types of connections.

MCP servers, hosts and clients

MCP uses a client-server architecture for the AI model to external system communication. The user connects to the AI application, referred to as the MCP host, such as IDEs like Cursor, AI chat apps like ChatGPT or AI agents. To connect to external services, the host creates one connection, referred to as the MCP client, to one external service, referred to as the MCP server. Therefore, to connect to multiple MCP servers, one host needs to open and manage multiple MCP clients.

Get started with MCP

You can deploy your first MCP server to Vercel with a single file. Then, you can connect to the server through popular MCP hosts like Claude or Cursor.

Deploy an MCP server on Vercel

Use the @vercel/mcp-adapter package and create the following API route to host an MCP server that provides a single tool that rolls a dice.

app/api/mcp/route.ts
import { createMcpHandler } from '@vercel/mcp-adapter';
 
const handler = createMcpHandler((server) => {
  server.tool(
    'roll_dice',
    'Rolls an N-sided die',
    { 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, handler as DELETE };

When you deploy your application on Vercel, you will get a URL such as https://my-mcp-server.vercel.app.

Configure an MCP host

Using Cursor, add the URL of your MCP server to the configuration file in SSE transport format.

SSE Server
{
  "mcpServers": {
    "server-name": {
      "url": "https://my-mcp-server.vercel.app/api/mcp"
    }
  }
}

You can now use your MCP roll dice tool in Cursor's AI chat or any other MCP client.

Deploy MCP servers efficiently on Vercel

By using Vercel to deploy your MCP server, you take advantage of Vercel Functions with Fluid compute to optimize your cost and usage. MCP servers often experience irregular usage patterns with a combination of long idle times, quick succession of messages and heavy AI workloads.

With Fluid compute's optimized concurrency and dynamic scaling, you only pay for the compute resources you actually use with the minimum amount of idle time. If your MCP server function needs to process AI heavy workloads, Fluid compute's ability to share instances increases performance efficiently.

More resources

Learn how to deploy MCP servers on Vercel, connect to them using the AI SDK, and explore curated lists of public MCP servers.

Last updated on May 28, 2025
Previous
Agents
Next
Integrations