How to Use the Lattice MCP in Vercel AI SDK

Q: How do I connect the Lattice MCP Server to Vercel AI SDK?

Install @ai-sdk/mcp and instantiate the client with your Vinkius HTTP URL. Pass mcpClient.tools() directly to streamText to let your LLM query listusers or listgoals on demand.

Q: Can I stream Lattice reviews using Vercel AI SDK?

Yes. Your agent can call listreviews to fetch active cycles, then immediately call getreview to pull specific cycle details, streaming the text directly to your React components.

Pipe live Lattice performance data straight to your Next.js app with the Vercel AI SDK and this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Lattice MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Render Lattice tasks in your Vercel AI SDK frontend

When your agent calls `list_tasks`, the Vercel AI SDK streams those pending items straight to the browser without a loading spinner. Your users don't want to wait for heavy HR portals to load when looking up their action items. By coupling `get_user` with this MCP Server and the Vercel AI SDK, you build tools where managers see real-time employee profiles pop up as they chat. No page refreshes or slow API fetches.

Build real-time Lattice feedback feeds with Vercel AI SDK

This MCP Server lets your Vercel AI SDK chatbot pull recent praise instantly via `list_feedback` and display it in a clean React component. Stop making managers dig through old email threads to find performance context. The SDK handles the heavy lifting of streaming raw JSON from `get_feedback` directly into structured UI blocks when a manager asks about a specific entry. It makes the entire review process feel instantaneous.

Stream Lattice OKR updates to Vercel AI SDK edge functions

Using `list_goals` with the Vercel AI SDK allows you to query active OKRs inside lightweight Edge Functions. You move your performance metrics to where your users actually work rather than forcing them to log into another system. When an employee wants a deep dive into a specific metric, your React frontend calls `get_goal` and streams the target details directly. It keeps your database connections clean and your app running fast.

Setup guide

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

Install `@ai-sdk/mcp` and instantiate the client with your Vinkius HTTP URL. Pass `mcpClient.tools()` directly to `streamText` to let your LLM query `list_users` or `list_goals` on demand.

Yes. Your agent can call `list_reviews` to fetch active cycles, then immediately call `get_review` to pull specific cycle details, streaming the text directly to your React components.

Yes, it does. The server connects via standard HTTP or SSE, allowing your edge-deployed Vercel AI SDK app to fetch employee profiles using `get_user` without cold-start issues.

You should handle rate limiting at your gateway layer. The SDK will report any 429 errors thrown when calling tools like `list_tasks`, allowing your UI to display a clean retry state.

Your Lattice employee records and API credentials never persist on Vinkius. Every call to `get_user` or `get_feedback` runs inside an isolated, ephemeral V8 sandbox that destroys its memory state immediately after the request completes.

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