MCP Tools

The AI SDK supports Model Context Protocol (MCP) tools by offering a lightweight client that exposes a tools method for retrieving tools from a MCP server. After use, the client should always be closed to release resources.

If you prefer to use the official transports (optional), install the official Model Context Protocol TypeScript SDK.

pnpm install @modelcontextprotocol/sdk
import {
experimental_createMCPClient,
generateText,
stepCountIs,
} from '@ai-sdk/mcp';
import { Experimental_StdioMCPTransport } from '@ai-sdk/mcp/mcp-stdio';
import { openai } from '@ai-sdk/openai';
// Optional: Official transports if you prefer them
// import { StdioClientTransport } from '@modelcontextprotocol/sdk/client/stdio';
// import { SSEClientTransport } from '@modelcontextprotocol/sdk/client/sse';
// import { StreamableHTTPClientTransport } from '@modelcontextprotocol/sdk/client/streamableHttp';
let clientOne;
let clientTwo;
let clientThree;
try {
// Initialize an MCP client to connect to a `stdio` MCP server (local only):
const transport = new Experimental_StdioMCPTransport({
command: 'node',
args: ['src/stdio/dist/server.js'],
});
const clientOne = await experimental_createMCPClient({
transport,
});
// Connect to an HTTP MCP server directly via the client transport config
const clientTwo = await experimental_createMCPClient({
transport: {
type: 'http',
url: 'http://localhost:3000/mcp',
// optional: configure headers
// headers: { Authorization: 'Bearer my-api-key' },
// optional: provide an OAuth client provider for automatic authorization
// authProvider: myOAuthClientProvider,
},
});
// Connect to a Server-Sent Events (SSE) MCP server directly via the client transport config
const clientThree = await experimental_createMCPClient({
transport: {
type: 'sse',
url: 'http://localhost:3000/sse',
// optional: configure headers
// headers: { Authorization: 'Bearer my-api-key' },
// optional: provide an OAuth client provider for automatic authorization
// authProvider: myOAuthClientProvider,
},
});
// Alternatively, you can create transports with the official SDKs instead of direct config:
// const httpTransport = new StreamableHTTPClientTransport(new URL('http://localhost:3000/mcp'));
// clientTwo = await experimental_createMCPClient({ transport: httpTransport });
// const sseTransport = new SSEClientTransport(new URL('http://localhost:3000/sse'));
// clientThree = await experimental_createMCPClient({ transport: sseTransport });
const toolSetOne = await clientOne.tools();
const toolSetTwo = await clientTwo.tools();
const toolSetThree = await clientThree.tools();
const tools = {
...toolSetOne,
...toolSetTwo,
...toolSetThree, // note: this approach causes subsequent tool sets to override tools with the same name
};
const response = await generateText({
model: openai('gpt-4o'),
tools,
stopWhen: stepCountIs(5),
messages: [
{
role: 'user',
content: [{ type: 'text', text: 'Find products under $100' }],
},
],
});
console.log(response.text);
} catch (error) {
console.error(error);
} finally {
await Promise.all([
clientOne.close(),
clientTwo.close(),
clientThree.close(),
]);
}