How to Use the ConfigCat MCP in Vercel AI SDK

Q: How do I add ConfigCat tools to my Vercel AI SDK stream?

You install @ai-sdk/mcp and create an MCP client pointing to the Vinkius endpoint. Pass the tools directly into streamText and close the connection when the stream finishes.

Q: Can Vercel AI SDK handle ConfigCat targeting rules at the edge?

Yes, the SDK evaluates these rules instantly. By calling getsettingvalue within your edge functions, the model retrieves the exact targeting state for any user ID without slowing down your stream.

Q: Does the ConfigCat MCP Server support Next.js Server Actions?

Absolutely. You can call tools like updatesettingvalue inside a Server Action, allowing your UI to trigger flag updates during standard form submissions or button clicks.

Toggle feature flags in real-time as your Next.js frontend streams responses using ConfigCat and 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 ConfigCat MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream live flag updates to Vercel AI SDK frontends

The `get_setting_value` tool lets your Vercel AI SDK client check ConfigCat feature states mid-response and render the correct UI immediately. Instead of waiting for a full page reload, the Vercel AI SDK hooks directly into these live ConfigCat values, letting users see UI components morph dynamically on the edge. You don't need heavy backend wrappers to toggle features on the fly. By passing `list_settings` to your Vercel AI SDK text generation function, you give the model the exact ConfigCat context it needs to render customized layouts without hitting database bottlenecks.

Manage environments on the edge with this MCP Server

The `create_environment` and `list_environments` tools let you spin up isolated ConfigCat test spaces directly from your Vercel AI SDK runtime. This MCP Server allows your edge-deployed Vercel AI SDK client to inspect active ConfigCat environments, verify deployment targets, and swap flags without leaving the serverless execution loop. Because Vercel AI SDK runs in lightweight edge functions, these ConfigCat tools execute with minimal latency. Your model gets the exact ConfigCat environment list, makes a decision, and streams the setup steps to your developer dashboard in real time.

Create targeting segments dynamically during chat sessions

The `create_segment` and `update_setting_value` tools allow your Vercel AI SDK chat interface to build custom ConfigCat user cohorts on the fly. While the user is talking to your Vercel AI SDK chat component, the underlying agent writes new targeting rules to ConfigCat based on the conversation context. This changes how you handle beta testing in Vercel AI SDK. Your streaming agent can instantly flag a user for a new ConfigCat feature group, update their access rules, and show them the newly unlocked frontend interface without a single manual deployment step.

Setup guide

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

You install `@ai-sdk/mcp` and create an MCP client pointing to the Vinkius endpoint. Pass the tools directly into `streamText` and close the connection when the stream finishes.

Yes, the SDK evaluates these rules instantly. By calling `get_setting_value` within your edge functions, the model retrieves the exact targeting state for any user ID without slowing down your stream.

Absolutely. You can call tools like `update_setting_value` inside a Server Action, allowing your UI to trigger flag updates during standard form submissions or button clicks.

The stream handles the error gracefully. You can set fallback values in your code so that if `get_setting_value` fails, your frontend defaults to a safe UI state.

Your API keys and feature flag configurations never touch public servers. Vinkius runs this MCP Server in an isolated V8 sandbox, passing only the final flag values back to your edge function.

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