How to Use the Fireflies.ai MCP in Vercel AI SDK

Q: How do I stream Fireflies.ai meeting summaries using the Vercel AI SDK?

Configure the MCP client in your route handler and call getaiappoutputs. Pass the tool output directly to streamText to push the summary to your React frontend block by block.

Q: Can I invite the recorder bot to a live call using Fireflies.ai and Vercel AI SDK?

Yes, execute addtolivemeeting directly from a server action. The SDK triggers the bot join request, letting your users bring the recorder into their Zoom or Teams call with one click.

Q: Does the Fireflies.ai MCP Server support file uploads when using Vercel AI SDK?

Yes, use uploadaudio inside your edge route to send the file stream directly to the API. Because the heavy transcription happens off-site, your Vercel AI SDK application avoids execution timeouts.

Q: Can I query meeting details directly from a chat interface?

Yes, bind askfred as a tool inside your streamText call. When a user asks a question, your agent calls the tool and streams the exact answer back to the chat.

Stream real-time meeting transcripts and AI summaries directly to your Next.js UI using 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 Fireflies.ai MCP to Vercel AI SDK

Create your Vinkius account to connect Fireflies.ai 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 Fireflies.ai with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream live meeting text into React views

`add_to_live_meeting` sends a silent bot to capture active calls, pumping real-time transcript data directly into your edge-compatible frontend. The Vercel AI SDK processes this incoming stream immediately, letting you render speaker blocks on the screen without waiting for the call to finish. Users watch words populate their browser in real time. Instead of staring at a loading spinner, your interface updates dynamically as the MCP Server delivers new chunks.

Build instant post-call UIs

`get_transcript` pulls full speaker text and metadata directly into your React or Svelte components. You pass this JSON payload directly into the SDK's text generation helpers to render clean, readable meeting minutes. For structured dashboards, `get_ai_app_outputs` fetches pre-formatted summaries and action items. This avoids manual parsing on the client side, keeping your edge functions fast and light.

Run serverless audio processing via MCP Server tools

`upload_audio` accepts local file uploads directly from a user-facing drop zone and triggers background transcription. Your Next.js backend passes the file stream to the MCP Server, keeping heavy processing off your serverless execution thread. If a meeting title needs a quick tweak from the UI, `update_meeting_title` updates the record instantly. This keeps your database and your meeting portal perfectly in sync.

Setup guide

Set up Fireflies.ai 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 Fireflies.ai 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 Fireflies.ai 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 Fireflies.ai. 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 Fireflies.ai 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 Fireflies.ai MCP in Vercel AI SDK

Configure the MCP client in your route handler and call `get_ai_app_outputs`. Pass the tool output directly to `streamText` to push the summary to your React frontend block by block.

Yes, execute `add_to_live_meeting` directly from a server action. The SDK triggers the bot join request, letting your users bring the recorder into their Zoom or Teams call with one click.

Yes, use `upload_audio` inside your edge route to send the file stream directly to the API. Because the heavy transcription happens off-site, your Vercel AI SDK application avoids execution timeouts.

Yes, bind `ask_fred` as a tool inside your `streamText` call. When a user asks a question, your agent calls the tool and streams the exact answer back to the chat.

The MCP Server runs in a secure sandbox, handling your API keys on the server side so they never leak to the client. Your raw meeting transcripts and audio files are processed over encrypted channels and never stored on intermediate 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