How to Use the Beeminder MCP in Vercel AI SDK

Q: How do I stream Beeminder goal updates using the Vercel AI SDK?

Install @ai-sdk/mcp and create a client pointing to your Vinkius endpoint. Use mcpClient.tools() to pass refreshgoal and getgoal directly into streamText for real-time frontend updates. Always call mcpClient.close() when the execution finishes.

Q: How do I modify Beeminder datapoints using the Vercel AI SDK?

Your agent can call updatedatapoint based on user input in the chat. The Vercel AI SDK streams this action live, updating your component's state as soon as Beeminder confirms the change.

Stream Beeminder goal updates directly into your Next.js frontend with 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 Beeminder MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Beeminder goals to your Vercel AI SDK UI

Stop making your users wait for API spinners just to see if they are in the red. This MCP Server exposes `get_goal_status` directly to your Edge Functions, allowing your Vercel AI SDK application to stream live progress charts directly into the viewport. When the agent calls `list_goals`, the SDK pushes the active graph data straight to the client. You get a live, ticking countdown of their Beeminder pledge safety buffer without writing polling loops or custom backend routes.

Log Beeminder datapoints with zero UI lag

Users can type a natural language update like "ran three miles" and watch their progress graph update instantly. The Vercel AI SDK executes `add_datapoint` and streams the confirmation payload immediately back to the React component. If they make a mistake, the agent can call `update_datapoint` or `delete_datapoint` on the fly. The SDK handles the raw JSON transport under the hood, so your frontend stays snappy and reactive.

Display Beeminder pledges and charges in your client

Keep users honest by showing them exactly what is at stake. The agent uses `list_charges` to fetch the real dollar amounts pledged on their current Beeminder road. By feeding this data through the SDK, the user sees their financial risk update dynamically as they chat. It turns a static productivity tool into an active, high-stakes dashboard.

Setup guide

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

Install `@ai-sdk/mcp` and create a client pointing to your Vinkius endpoint. Use `mcpClient.tools()` to pass `refresh_goal` and `get_goal` directly into `streamText` for real-time frontend updates. Always call `mcpClient.close()` when the execution finishes.

Yes, the server runs on Vinkius's V8 sandboxed environment, making it lightweight and fast. The Vercel AI SDK connects to it via standard HTTP transport, which is fully compatible with Edge runtimes.

Vinkius manages the underlying OAuth tokens for you, giving you a single secure endpoint. Your Vercel AI SDK setup only needs to pass the Vinkius authorization header to access `get_user_info` safely.

Your agent can call `update_datapoint` based on user input in the chat. The Vercel AI SDK streams this action live, updating your component's state as soon as Beeminder confirms the change.

Your Beeminder API keys and pledge details are isolated inside Vinkius's zero-trust sandbox. The SDK only receives the specific JSON payloads returned by tools like `list_datapoints`, keeping your personal account secure.

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