How to Use the Mela MCP in Vercel AI SDK

Q: How do I connect the Mela MCP Server to my Vercel AI SDK project?

Install the @ai-sdk/mcp package and use createMCPClient to connect to the Mela endpoint. Pass the tools directly into streamText or generateText and remember to call mcpClient.close() when the session ends.

Q: Can the AI client update checklists in real-time?

It can. Your agent uses listchecklists to fetch active tasks and then uses updateactivitystatus to close out completed items, streaming the updates straight to your UI.

Stream Mela site updates and material logs directly into your Vercel AI SDK frontend without loading spinners.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mela MCP to Vercel AI SDK

Create your Vinkius account to connect Mela 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 Mela with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time site status updates in your Vercel AI SDK UI

`list_activities` lets your Vercel AI SDK application pull active job sites and render them instantly on the client side. Our MCP Server lets your web interface bypass slow database queries by fetching active jobs on demand. When a supervisor updates progress, `update_activity_status` pushes that state change directly through your active streaming components. Your Next.js dashboard updates live without requiring manual page refreshes.

Live cost tracking and material logging

`log_materials` sends consumption updates from the field straight to your Vercel AI SDK streaming interface. Office admins watch drywall or concrete logs pop up on their screen as laborers input them. Your agent processes financial data using `get_accounting_data` to calculate budget burn rates instantly. This lets your web app render live SVG cost charts that shift as new resource logs arrive.

Instant work hour logging via streaming chat

`log_work_hours` records labor times directly from a conversational input box in your React app. Workers type a quick update, and the SDK streams the parsed hours straight to the Mela database. Your app confirms the log by invoking `get_me` to verify the active worker's profile. This validation happens mid-stream so users get instant feedback in the chat window.

Setup guide

Set up Mela 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 Mela 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 Mela 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 Mela. 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 Mela 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 Mela MCP in Vercel AI SDK

Install the `@ai-sdk/mcp` package and use `createMCPClient` to connect to the Mela endpoint. Pass the tools directly into `streamText` or `generateText` and remember to call `mcpClient.close()` when the session ends.

Yes, this MCP Server works perfectly on Vercel Edge Functions. The lightweight HTTP transport ensures fast startup times without cold-start delays when running tools like `post_message`.

The Vinkius platform handles the underlying OAuth or token exchange for Mela. You configure the `authProvider` in your SDK client setup, which lets your users run `get_me` securely.

It can. Your agent uses `list_checklists` to fetch active tasks and then uses `update_activity_status` to close out completed items, streaming the updates straight to your UI.

Your labor logs, material costs, and team lists remain inside Vinkius's secure V8 isolates. The MCP only receives the specific data payloads returned by tools like `get_accounting_data` without exposing credentials.

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