How to Use the COR MCP in Vercel AI SDK

Q: Can I stream COR task details live using Vercel AI SDK?

Yes, you can. By calling getcortask through the MCP client, the tool outputs task statuses directly into streamText, letting your users see detailed updates render word-by-word in your UI.

Q: How do I fetch the active user details?

Use the getcorme tool within your agent's execution block. This returns the authenticated user's profile and permissions, allowing you to scope the interface options based on their agency role.

Stream COR agency margins directly into your Next.js frontend in real-time using the Vercel AI SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect COR MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time margin tracking for Next.js apps

The `list_cor_projects` tool exposes real-time project profitability metrics directly to your client interface. Instead of waiting for a heavy page reload, your app streams live financial health data directly into your dashboard as your agent pulls it from COR. This setup lets you build live-updating client portals. Your users watch their project statuses change on the fly as your Vercel AI SDK client updates the view with zero lag.

Dynamic task and project generation via MCP Server

The `create_cor_project` tool lets your streaming frontend build new agency workspaces instantly. When an account manager requests a new client workspace, your agent triggers the creation flow and renders the new project details in the UI without a spinner. You get a highly interactive workspace where teams spin up tasks using `list_cor_task_types` on the fly. Your frontend code maps these options directly into React components through this MCP connection while the stream is active.

Live resource allocation and team monitoring

The `list_cor_team_members` tool pulls active agency staff lists directly into your React or Vue components. Your AI client matches available developers and designers to open tasks, balancing workloads based on current project assignments. By combining this with `list_cor_time_entries`, your app displays exact hours logged against active budgets. Your users see live margin updates as their team logs hours throughout the day.

Setup guide

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

You handle authentication by passing an endpoint token during the MCP client setup. The Vercel AI SDK uses the MCP client to securely pass credentials to Vinkius, meaning your frontend never exposes raw API keys.

Yes, you can. By calling `get_cor_task` through the MCP client, the tool outputs task statuses directly into streamText, letting your users see detailed updates render word-by-word in your UI.

Always call mcpClient.close() when your streaming session finishes. This prevents open connections from hanging in your Edge Functions and keeps your serverless execution clean.

Use the `get_cor_me` tool within your agent's execution block. This returns the authenticated user's profile and permissions, allowing you to scope the interface options based on their agency role.

Absolutely. All requests to fetch agency time logs and project margins run inside secure V8 isolates. Vinkius never stores your COR credentials or database records, acting purely as an ephemeral bridge.

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