How to Use the 100ms MCP in Vercel AI SDK

Q: Can Vercel AI SDK list active 100ms participants?

Your agent uses listpeers to find everyone currently in a room. You then stream these names directly into your UI components for a live participant list.

Q: How can I update 100ms room settings via my AI?

Use the updateroom tool within your agent's tool set. Simply ask the AI to change the room configuration, and it will trigger the update automatically.

Stream 100ms video room data directly into your Vercel AI SDK frontends for live, interactive meeting interfaces.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect 100ms MCP to Vercel AI SDK

Create your Vinkius account to connect 100ms 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 100ms with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build real-time video dashboards

Your React components pull live meeting metadata as your AI streams text responses. Users see active participant lists populate their UI the second the agent calls `list_peers` without waiting for a full page refresh. This removes the lag between querying meeting status and showing it to your users. You avoid manual polling and complex state management by letting the agent push 100ms updates directly into your stream.

Automate room configuration

Your agent triggers `create_room` or `update_room` based on natural language commands from your users. The interface reflects these settings instantly, ensuring your video infrastructure stays in sync with user requests. You stop writing boilerplate code to handle room settings. Everything happens inside the standard Vercel AI SDK flow, keeping your logic contained in one place.

Surface session history instantly

Your frontends display past session details by calling `list_sessions` through your agent. You get clean, typed data back that renders immediately in your Next.js views. You eliminate the need for custom backend endpoints just to fetch basic 100ms metadata. The agent handles the data retrieval, and your UI handles the display.

Setup guide

Set up 100ms 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 100ms 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 100ms 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 100ms. 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 100ms 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 100ms MCP in Vercel AI SDK

Install the necessary packages and initialize the client using your Vinkius endpoint token. You pass the tools into your streamText or generateText calls, allowing your AI to execute 100ms operations as part of its normal response cycle.

Yes, it runs on the edge when using the HTTP transport provided by Vinkius. This keeps your latency low for user-facing applications that need to interact with video infrastructure.

Your agent uses `list_peers` to find everyone currently in a room. You then stream these names directly into your UI components for a live participant list.

Use the `update_room` tool within your agent's tool set. Simply ask the AI to change the room configuration, and it will trigger the update automatically.

Your meeting metadata stays secure because every request runs within a V8 Isolate sandbox. This ephemeral execution environment ensures your room details are processed safely without persistent storage on our servers.

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