How to Use the Bilflo MCP in Vercel AI SDK

Q: How do I configure Bilflo with the Vercel AI SDK?

Call createMCPClient with the Vinkius transport URL, then pass the tools directly to generateText or streamText. Remember to call mcpClient.close() when the session ends to prevent memory leaks.

Q: Does the Vercel AI SDK support Bilflo authentication?

Yes, you can pass your credentials securely using the authProvider option in the SDK configuration. Vinkius manages the secure connection, so your frontend never exposes raw API keys.

Feed Bilflo contractor records and timecards directly into 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 Bilflo MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live-stream staffing data via Vercel AI SDK

Your users don't want to stare at a loading spinner while fetching contractor details. It's a waste of time. This MCP Server lets your Next.js frontend stream real-time staffing updates directly into React components. When the agent calls `get_contractor` or `list_contractors`, the data renders instantly as it arrives. You set this up by calling `mcpClient.tools()` and passing the array directly into `streamText`. That's it. No manual API glue code is required to bridge your frontend with Bilflo.

Query placements and overtime rules on the Edge

Edge functions demand fast execution when querying Bilflo placement data without cold starts. Speed is everything. Your agent can call `list_placements` and `list_overtime_rules` to evaluate billing rules on the fly using this MCP Server. Because Vinkius handles the underlying authentication, you don't have to manage complex OAuth handshakes inside your Next.js edge middleware to query Bilflo. The agent handles the tool calls, and you close the connection with `mcpClient.close()` when the stream ends.

Instant timecard feeds without spinners

Frontends built with the Vercel AI SDK can render interactive tables the second a billing query finishes. It's that fast. Your agent uses `list_timecards` or `get_timecard` to pull hours worked, sending the raw data straight to your custom UI components. You construct the Bilflo connection using `createMCPClient` and point it to the Vinkius endpoint. The UI updates incrementally, letting managers verify hours without page refreshes.

Setup guide

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

Call `createMCPClient` with the Vinkius transport URL, then pass the tools directly to `generateText` or `streamText`. Remember to call `mcpClient.close()` when the session ends to prevent memory leaks.

Yes, the Vercel AI SDK handles this by feeding tool outputs from `list_contractors` directly into your UI components. The data renders in real-time as the agent receives it, bypassing traditional API endpoints.

Yes, you can pass your credentials securely using the `authProvider` option in the SDK configuration. Vinkius manages the secure connection, so your frontend never exposes raw API keys.

Yes, the entire setup is compatible with Edge environments. It relies on standard HTTP transports, keeping the bundle size small and execution times fast when retrieving client data.

Your staffing data remains completely private. Vinkius runs this MCP Server in an isolated V8 sandbox, meaning contractor records and timecard hours are never stored or logged on external servers. All data transfers use encrypted HTTPS connections directly to your AI client.

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