How to Use the Daily.co MCP in Vercel AI SDK

Q: How do I connect the Daily.co MCP Server to Vercel AI SDK?

Install @ai-sdk/mcp and instantiate createMCPClient. Point the HTTP transport to your Vinkius endpoint, then pass mcpClient.tools() into streamText. Always call close() when the route finishes.

Q: Can Vercel AI SDK kick users out of a Daily.co room?

Yes. The agent calls ejectparticipants with the specific user ID. The WebRTC connection drops immediately, and the frontend updates the participant list.

Q: How do I handle Daily.co webhooks in Vercel AI SDK?

Use createwebhook to point Daily.co events to a Next.js API route. Your agent can also read failing endpoints using getwebhook and fix them via updatewebhook.

Build real-time video dashboards in React with Vercel AI SDK handling the backend WebRTC API calls on the fly.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Daily.co MCP to Vercel AI SDK

Create your Vinkius account to connect Daily.co 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 Daily.co with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Spawn video calls via Vercel AI SDK

The `create_room` and `create_meeting_token` tools let your Vercel AI SDK client spin up secure video sessions instantly. You pass the user prompt to the edge function, and the agent provisions a private URL before the text finishes streaming to the frontend. Managing access is just as fast. Call `update_permissions` to flip a participant's camera on or off based on chat commands. The React UI updates immediately because the MCP Server executes the state change in milliseconds.

Control RTMP feeds and cloud recordings

Your agent triggers `start_live_streaming` to push WebRTC feeds out to HLS or custom RTMP endpoints. It works directly from the chat interface. You type 'broadcast this session,' and the backend handles the layout configuration. Fetching the playback files happens through `get_recording_access_link`. The SDK streams the temporary S3 URL right into a video player component. Users never see a loading state while the system pulls the asset.

Stream session data to the UI

Tools like `get_global_presence` and `get_room_presence` feed active participant counts straight to your Next.js dashboard. The AI client polls the Daily.co infrastructure and pushes the exact number of active connections to the DOM. Tracking drop-offs requires `get_logs`. You ask the agent why a specific user disconnected, and it reads the raw call metrics to pinpoint network failures. The explanation streams into the chat window alongside the raw data.

Setup guide

Set up Daily.co 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 Daily.co 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 Daily.co 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 Daily.co. 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 Daily.co 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 Daily.co MCP in Vercel AI SDK

Install `@ai-sdk/mcp` and instantiate `createMCPClient`. Point the HTTP transport to your Vinkius endpoint, then pass `mcpClient.tools()` into `streamText`. Always call `close()` when the route finishes.

Yes. The agent calls `eject_participants` with the specific user ID. The WebRTC connection drops immediately, and the frontend updates the participant list.

The MCP protocol runs over standard HTTP. You trigger the API calls from your edge routes without bundling heavy SDKs. The response time stays under the edge execution limits.

Use `create_webhook` to point Daily.co events to a Next.js API route. Your agent can also read failing endpoints using `get_webhook` and fix them via `update_webhook`.

Vinkius routes the traffic through an ephemeral V8 Isolate Sandbox. The agent reads raw network metrics and participant IDs via `get_logs`, but the sandbox destroys memory immediately after returning the payload to your UI. Nothing persists on our end.

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