How to Use the Metorial MCP in Vercel AI SDK

Q: How do I initialize Metorial inside a Vercel AI SDK project?

Install @ai-sdk/mcp and call createMCPClient with your HTTP endpoint. Pass the tools directly to streamText and remember to call mcpClient.close when the execution finishes.

Q: Can Vercel AI SDK handle cold starts when calling metorialinvokeservertool?

Yes. Your application can run metorialgetserverstatus to verify the container is warm before initiating the tool call.

Q: How does Metorial manage serverless compute costs for a Vercel AI SDK setup?

Run metorialgetusagemetrics to track active execution times. You can trigger metorialdeleteserver to shut down idle nodes automatically when users disconnect.

Q: Can I trace Vercel AI SDK tool execution failures using Metorial?

Use metoriallisttraces to locate the stuck transaction ID. You can then pull the exact execution boundary details to debug the timeout in your local terminal.

Send telemetry from serverless MCP agents directly to your frontend with Vercel AI SDK and Metorial.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Metorial MCP to Vercel AI SDK

Create your Vinkius account to connect Metorial to Vercel AI SDK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Metorial with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live trace rendering in Vercel AI SDK

`metorial_list_traces` lets your frontend application fetch and display agent transaction logs in real time. Instead of hiding execution steps behind a loading spinner, your UI gets a live feed of exactly what the agent is doing. You read the raw execution state using `metorial_get_trace_details` to show step-by-step agent decisions. Users watch the backend work, which makes long-running tasks feel instantaneous.

Real-time container metrics on the Edge

`metorial_get_usage_metrics` pulls live compute cost and latency statistics directly into your Edge Functions. You don't need a heavy database connection to track how much memory your serverless MCP instances consume. This tool exposes execution times and resource limits with zero cold-start overhead. Your Vercel AI SDK application can automatically flag slow tool executions before they impact the user experience.

Dynamic MCP Server lifecycle management

`metorial_deploy_server` provisions a dedicated serverless container whenever your application needs to scale up agent capacity. You control the logical matrix directly from your TypeScript frontend. When the user session ends, `metorial_delete_server` tears down the inactive instance to stop the billing meter. This keeps your cloud spend tight while maintaining high availability for active users.

Setup guide

Set up Metorial MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Metorial tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Metorial transactions",
});

console.log(text);
await mcpClient.close();

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Metorial. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Metorial now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Metorial MCP in Vercel AI SDK

Install `@ai-sdk/mcp` and call `createMCPClient` with your HTTP endpoint. Pass the tools directly to `streamText` and remember to call `mcpClient.close` when the execution finishes.

Yes. Your application can run `metorial_get_server_status` to verify the container is warm before initiating the tool call.

Run `metorial_get_usage_metrics` to track active execution times. You can trigger `metorial_delete_server` to shut down idle nodes automatically when users disconnect.

Use `metorial_list_traces` to locate the stuck transaction ID. You can then pull the exact execution boundary details to debug the timeout in your local terminal.

All transaction logs and logical server configurations remain inside an isolated zero-trust sandbox. Your Vercel AI SDK client accesses this telemetry through encrypted HTTP endpoints, ensuring no raw agent data leaks to external third parties.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript