How to Use the Float MCP in Vercel AI SDK

Stream real-time resource data from Float directly into your Vercel AI SDK interface without the loading spinners.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Float MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live allocation updates in your UI

Feed your UI with live data by calling `list_allocations`. Your users see the schedule shifting as the agent processes changes. Stop forcing users to wait for batch refreshes. The Vercel AI SDK handles these tool outputs as a stream, so the interface stays responsive while the data settles.

Direct project management via MCP Server

Trigger `create_allocation` directly from your frontend logic. Your AI client acts as the bridge between user intent and your resource calendar. It’s about cutting the round-trip latency. You define the flow, and the MCP Server executes the command immediately against the Float backend.

Context-aware team filtering

Pass specific department IDs into `list_people` to narrow down the view. Your AI client builds a focused persona based on who is actually available. Don't dump the entire company directory into the context window. Use the tools to fetch only what the specific view requires for that user session.

Setup guide

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

Initialize the client using the provided HTTP transport and pass the tools into your `generateText` call. This grants your agent the ability to execute functions like `get_project` directly.

Float enforces API rate limits that you need to monitor. If your agent makes rapid calls, cache the results locally or implement a request queue to avoid hitting those caps.

The server operates within a V8 isolate sandbox. Only the tools you explicitly call get access to your project records, ensuring no data leaks beyond the specified scope.

No. You connect the Vercel AI SDK directly to the managed endpoint. Vinkius handles the underlying infrastructure and authentication for you.

The agent only sees what the tools allow, such as project names, allocation blocks, and logged time entries. It never touches your raw authentication credentials or sensitive client metadata.

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