How to Use the Unleash (Feature Toggles) MCP in Vercel AI SDK

Q: How do I check feature flags with Unleash (Feature Toggles) and Vercel AI SDK?

Call the getclientfeatures tool. Your agent reads all feature flags and strategies for server-side evaluation, letting you know what features are active right now.

Q: Does Unleash (Feature Toggles) support listing projects with Vercel AI SDK?

Yeah, it does. The listprojects tool fetches all configured project IDs for you. This is critical if your code needs to target a specific deployment.

Q: Can I see available environments with Unleash (Feature Toggles) and Vercel AI SDK?

Sure. The listenvironments tool pulls every environment defined in your account. This lets you test feature toggles across staging, production, or any other setting.

Q: How do I register a new backend instance with Unleash (Feature Toggles) and Vercel AI SDK?

You call registerclient to register a new backend SDK instance. This makes sure the MCP Server knows where your code is running when reporting usage metrics.

Real-time Feature Toggles Streaming into your Next.js UI with 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 Unleash (Feature Toggles) MCP to Vercel AI SDK

Create your Vinkius account to connect Unleash (Feature Toggles) 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 Unleash (Feature Toggles) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Check Features Directly in the Frontend

You can use `get_client_features` to fetch all feature flags and strategies for server-side evaluation. This means your agent knows exactly what features are active before sending data back.

List All Unleash Projects via MCP Server

Need a list of available projects? Call `list_projects` to get all configured project IDs. You'll also find `list_environments`, which fetches every environment set up in your account.

Track Usage with SDK Metrics Reporting

After you run code, report how often a feature was used using `report_client_metrics`. This sends flag usage data from the backend back through the MCP Server for tracking. You can also use `report_frontend_metrics` to track client-side behavior.

Setup guide

Set up Unleash (Feature Toggles) 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 Unleash (Feature Toggles) 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 Unleash (Feature Toggles) 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 Unleash. 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 Unleash (Feature Toggles) 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 Unleash (Feature Toggles) MCP in Vercel AI SDK

Call the `get_client_features` tool. Your agent reads all feature flags and strategies for server-side evaluation, letting you know what features are active right now.

Yeah, it does. The `list_projects` tool fetches all configured project IDs for you. This is critical if your code needs to target a specific deployment.

This MCP Server touches user configuration data, specifically `list_users`. Your agent can fetch all configured users, which helps map feature flags to specific people.

Sure. The `list_environments` tool pulls every environment defined in your account. This lets you test feature toggles across staging, production, or any other setting.

You call `register_client` to register a new backend SDK instance. This makes sure the MCP Server knows where your code is running when reporting usage metrics.

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