How to Use the Fellow MCP in Vercel AI SDK

Q: How do I configure Fellow tool streaming with Vercel AI SDK?

Install @ai-sdk/mcp and initialize the client using the Vinkius HTTP transport URL. Pass the tools from the client directly into streamText to let your agent call listmeetings or listactionitems during a live chat session.

Q: Can I use Fellow and Vercel AI SDK to filter action items by status?

Yes, you can pass the status parameter to listactionitems to filter by pending, completed, or archived tasks. The Vercel AI SDK then streams only the matching tasks straight to your user's dashboard via the MCP Server.

Q: How does Vercel AI SDK handle Fellow user lookups?

Your agent calls listusers to match team members by email or name. The SDK streams this user directory directly into your UI dropdowns for quick assignment.

Q: How do I verify the API connection before starting a stream?

You can call checkfellowstatus to verify active API connectivity before initiating a stream. If the check fails, your Next.js app can gracefully fall back to a cached state.

Build real-time meeting dashboards with the Fellow MCP Server streaming directly into your Vercel AI SDK frontend.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Fellow MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream meeting agendas to Vercel AI SDK UI

`list_notes` pulls the raw content of your meeting notes directly into your Next.js frontend. Your AI client reads the meeting structure and renders it live as the user watches, bypassing slow loading screens. By calling `get_note`, you extract specific action points and sync them to your components instantly. This setup runs on Edge Functions to keep latency low.

Manage tasks directly in the Vercel AI SDK chat

`create_action_item` lets your users assign tasks to team members by email directly from a chat interface. The Vercel AI SDK streams the success state of the new task without requiring page refreshes. You can also trigger `complete_action_item` when a user clicks a custom UI button. The interface updates in real time to show the task is resolved in your workspace.

Query Fellow MCP Server streams on the edge

`list_streams` retrieves recurring meeting series details to build dynamic schedule views. This MCP Server integration allows your edge-deployed Vercel AI SDK application to fetch current workspace streams. Running `get_stream` lets you fetch metadata for specific recurring series on demand. Your frontend displays these updates immediately using React Server Components.

Setup guide

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

Install `@ai-sdk/mcp` and initialize the client using the Vinkius HTTP transport URL. Pass the tools from the client directly into `streamText` to let your agent call `list_meetings` or `list_action_items` during a live chat session.

Yes, you can pass the status parameter to `list_action_items` to filter by pending, completed, or archived tasks. The Vercel AI SDK then streams only the matching tasks straight to your user's dashboard via the MCP Server.

Your agent calls `list_users` to match team members by email or name. The SDK streams this user directory directly into your UI dropdowns for quick assignment.

You can call `check_fellow_status` to verify active API connectivity before initiating a stream. If the check fails, your Next.js app can gracefully fall back to a cached state.

Yes, your actual meeting notes and stream details are processed inside Vinkius's secure V8 isolates. This zero-trust MCP architecture ensures the SDK only receives the specific JSON payloads returned by `get_note` over encrypted HTTPS connections.

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