How to Use the Metisscan (Metis L2 Network Explorer) MCP in Vercel AI SDK

Q: How do I connect the Metisscan (Metis L2 Network Explorer) to my Vercel AI SDK project?

Install @ai-sdk/mcp and set up an HTTP transport to point to the Vinkius endpoint. You then register the server tools by calling mcpClient.tools() and passing them directly to streamText.

Your users see live Metis L2 block and transaction data render instantly as the Vercel AI SDK streams the raw JSON payloads.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Metisscan (Metis L2 Network Explorer) MCP to Vercel AI SDK

Create your Vinkius account to connect Metisscan (Metis L2 Network Explorer) 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 Metisscan (Metis L2 Network Explorer) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Live L2 State to React with this MCP Server

This MCP Server exposes JSON-RPC tools like `eth_block_number` and `eth_get_balance` directly to your client. Your AI agent grabs the latest Metis block state or address balances and formats them instantly for the user. Real-time rendering happens because the Vercel AI SDK streams these tool outputs token-by-token. Instead of staring at a blank loading screen, your users watch the L2 blockchain state populate their UI live.

Verify Smart Contracts on the Fly

Running `get_smart_contract` and `get_smart_contract_verification_config` lets your agent verify deployed bytecode right inside your chat interface. The client inspects the actual verification configuration to ensure the contract logic matches the expected source code. You don't have to build custom UI components for every smart contract inspection. Vercel AI SDK handles the raw data stream from the Metis network, rendering the code blocks as soon as the explorer returns them.

Inspect Token Holders and Transfers Instantly

Executing `get_token_holders` and `get_token_transfers` gives your agent immediate access to Metis L2 asset distribution. The agent parses the distribution list and calculates holder concentration on the fly. By integrating these tools with the Vercel AI SDK, your application displays live token analytics without lag. Your users get the breakdown of Metis token movements in real-time, right as they ask for it.

Setup guide

Set up Metisscan (Metis L2 Network Explorer) 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 Metisscan (Metis L2 Network Explorer) 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 Metisscan (Metis L2 Network Explorer) 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 Metisscan. 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 Metisscan (Metis L2 Network Explorer) 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 Metisscan (Metis L2 Network Explorer) MCP in Vercel AI SDK

Install `@ai-sdk/mcp` and set up an HTTP transport to point to the Vinkius endpoint. You then register the server tools by calling `mcpClient.tools()` and passing them directly to `streamText`.

Yes, this integration runs perfectly on the edge because the HTTP transport is lightweight. Your serverless functions call tools like `graphql_query` without violating standard edge runtime limits.

The SDK passes the query execution to the Vinkius proxy, which manages the underlying rate limits for tools like `list_transactions`. You only need to handle normal API error states in your application code.

The Vercel AI SDK catches the RPC error thrown by the explorer and passes the failure message directly to your agent. Your agent can then explain the revert reason or gas issue to the user.

No, this server only processes public blockchain data like transactions, contract bytecode, and wallet balances. Vinkius runs the server in an ephemeral sandbox, meaning your API queries leave no storage footprint.

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