How to Use the TollGuru MCP in Vercel AI SDK

Q: Can I get multi-stop results using TollGuru with Vercel AI SDK?

Yep. Use calculatetollmultistop. It's designed for complex delivery routes that involve several waypoints. The agent calculates the tolls and costs at every single plaza along that extended trip.

Q: Does TollGuru support different vehicle types with Vercel AI SDK?

Absolutely. The calculatetollroute tool supports everything from 2-axle cars to massive commercial trucks (up to 9+ axles). You just specify the vehicle type, and the server handles the rest of the toll calculation.

Q: Is TollGuru reliable for post-trip reconciliation with Vercel AI SDK?

Yes. The calculatetollfrompolyline tool is built specifically for this. If you have a GPS track from a trip, you feed it here to get the exact toll costs and fuel consumption details needed for reconciliation.

Real-time trip cost visualization powered by 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 TollGuru MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Visualize complex route costs live.

Use `calculate_toll_route` when a user asks for the full toll breakdown between two points. The result streams directly into your UI, showing plaza names, tag costs, and fuel estimates as they calculate. This means users see the total trip cost update in real-time without waiting for a final loading screen. When building frontends with Vercel AI SDK, this streaming capability is huge. You can show granular data—like accepting payment methods or suggesting route changes—as your agent figures out the best path across multiple states.

Process pre-mapped GPS paths.

Need to calculate tolls for a polyline provided by Google Maps? Call `calculate_toll_from_polyline`. This tool takes an existing route and spits out the necessary toll, fuel, and cost details. It handles all vehicle types, so you don't have to worry about building separate logic for trucks or motorcycles. This is perfect for integrating TollGuru results into mapping apps that already process routes. You just feed them the polyline data, and your AI client shows the accurate toll costs immediately.

Manage multi-stop logistics trips.

Don't just calculate point A to point B; handle complex deliveries. `calculate_toll_multi_stop` breaks down tolls for every plaza along a route with multiple waypoints. It also factors in fuel and optional driver costs, giving your user a complete budget. When pairing TollGuru with the Vercel AI SDK, you can let users input five stops and watch the total cost estimate update live as the agent processes the entire multi-stop journey.

Setup guide

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

When your client uses the Vercel AI SDK, it calls a specific MCP tool like `calculate_toll_route`. The server runs the calculation and streams the detailed result back to your front end. This lets users see the toll breakdown appear piece by piece.

TollGuru handles routing details, including origin/destination points and specific polyline coordinates from mapping services. The output includes calculated cost metrics like tolls, fuel costs, and optional driver time values.

Yep. Use `calculate_toll_multi_stop`. It's designed for complex delivery routes that involve several waypoints. The agent calculates the tolls and costs at every single plaza along that extended trip.

Absolutely. The `calculate_toll_route` tool supports everything from 2-axle cars to massive commercial trucks (up to 9+ axles). You just specify the vehicle type, and the server handles the rest of the toll calculation.

Yes. The `calculate_toll_from_polyline` tool is built specifically for this. If you have a GPS track from a trip, you feed it here to get the exact toll costs and fuel consumption details needed for reconciliation.

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