Can my AI calculate the total toll costs for a road trip from New York to Boston?

Yes! Use the `calculate_toll_route` tool with origin="New York, NY" and destination="Boston, MA". You can specify your vehicle type (2AxlesAuto for regular cars, 2AxlesEV for electric vehicles, or truck types like 5AxlesTruck for commercial vehicles). The API returns detailed toll plaza names, tag and cash costs for each plaza, total toll cost, fuel cost estimate, and optional driver cost. You can also request costs in different currencies and compare payment methods (tag vs cash vs prepaid card

How do I get toll costs for a route I already have from Google Maps?

Use the `calculate_toll_from_polyline` tool with the encoded polyline from Google Maps. Set source="google" and paste the polyline string. This calculates tolls for your exact route without re-routing. You can also specify vehicle type and currency. This is perfect when you have an existing route and need toll costs for trip budgeting or fleet expense tracking.

Can I optimize a multi-stop delivery route to minimize toll costs?

Absolutely! Use the `calculate_toll_multi_stop` tool with your origin, destination, and comma-separated waypoints. Set optimize_waypoints="true" to let TollGuru find the most cost-effective waypoint order. The API returns the optimized route with total toll costs, fuel costs, and detailed plaza-by-plaza breakdown. This is essential for logistics planning, delivery route optimization, and fleet cost management.

TollGuru MCP Server for Pydantic AI 3 tools — connect in under 2 minutes

Name: TollGuru
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 3 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect TollGuru through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to TollGuru "
            "(3 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in TollGuru?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About TollGuru MCP Server

Connect your TollGuru toll calculation API to any AI agent and take full control of trip cost estimation, toll plaza tracking, route optimization, and fleet expense management across 50+ countries through natural conversation.

Pydantic AI validates every TollGuru tool response against typed schemas, catching data inconsistencies at build time. Connect 3 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Toll Calculation — Calculate toll costs for any route with detailed plaza-by-plaza breakdown including tag and cash prices
Fuel Cost Estimation — Get fuel cost estimates based on vehicle efficiency and current fuel prices along the route
Driver Cost Analysis — Calculate driver costs based on hourly wage or time value for complete trip budgeting
Multi-Stop Routes — Calculate tolls for routes with multiple waypoints and optimize waypoint order to minimize tolls
Route Optimization — Find the most cost-effective route between origin and destination with toll-aware routing
Polyline Toll Calculation — Calculate tolls for existing routes from Google Maps, Here Maps, or Mapbox polylines
Vehicle-Specific Pricing — Get accurate toll costs for any vehicle type from 2-axle cars to 9-axle commercial trucks
Multi-Currency Support — View costs in USD, CAD, MXN, EUR, GBP, INR, AUD, and 12+ other currencies
Payment Method Breakdown — Compare toll costs by payment method (tag, cash, prepaid card, license plate)
Global Coverage — Calculate tolls across US, Canada, Mexico, Europe, Australia, India, and 50+ countries

The TollGuru MCP Server exposes 3 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect TollGuru to Pydantic AI via MCP

Follow these steps to integrate the TollGuru MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 3 tools from TollGuru with type-safe schemas

Why Use Pydantic AI with the TollGuru MCP Server

Pydantic AI provides unique advantages when paired with TollGuru through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your TollGuru integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your TollGuru connection logic from agent behavior for testable, maintainable code

TollGuru + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the TollGuru MCP Server delivers measurable value.

Type-safe data pipelines: query TollGuru with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple TollGuru tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query TollGuru and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock TollGuru responses and write comprehensive agent tests

TollGuru MCP Tools for Pydantic AI (3)

These 3 tools become available when you connect TollGuru to Pydantic AI via MCP:

calculate_toll_from_polyline

This is useful when you already have a route from a mapping service and need toll calculations without re-routing. Returns the same detailed toll, fuel, and cost information as the route calculation. Supports all vehicle types, currencies, and payment methods. Essential for integrating with existing mapping applications, post-trip toll reconciliation, and GPS track-based toll analysis. AI agents should use this when users have an existing route polyline from Google Maps, Here Maps, or another service and need toll costs for that specific route. Calculate tolls for a route defined by an encoded polyline from any mapping service

calculate_toll_multi_stop

Returns detailed breakdown of tolls at each plaza along the complete route, fuel costs, and optional driver costs. Supports waypoint optimization to minimize total toll costs. Essential for delivery route planning, multi-stop trip budgeting, and logistics optimization. AI agents should use this when users need toll calculations for routes with multiple stops, such as "calculate tolls from Chicago to Detroit with stops in Toledo and Ann Arbor" or "what are the toll costs for my delivery route with 5 waypoints". Calculate tolls for a multi-stop route with multiple waypoints

calculate_toll_route

Returns detailed toll plaza information including plaza names, tag and cash costs, payment methods accepted, and route optimization suggestions. Also calculates fuel costs based on vehicle efficiency and current fuel prices, and optional driver costs based on time value. Supports all vehicle types including 2-axle cars, EVs, motorcycles, and commercial trucks (2-9+ axles). You can request route optimization to minimize toll costs, specify currency output (USD, CAD, MXN, EUR, GBP, INR, AUD, etc.), and choose mapping service (Here Maps, Google Maps, or TollGuru internal). Essential for fleet management, trip cost estimation, route planning, toll reconciliation, and travel budgeting. AI agents should use this when users ask "what are the tolls from New York to Boston", "calculate toll costs for my truck from LA to San Francisco", or need comprehensive trip cost breakdowns including tolls, fuel, and driver time. Calculate tolls and total trip costs for a route with origin, destination, and optional waypoints

Example Prompts for TollGuru in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with TollGuru immediately.

"Calculate toll costs for a car trip from San Francisco to Los Angeles."

"What are the toll costs for a 5-axle truck from Chicago to Detroit?"

"Optimize a delivery route with stops in Philadelphia, Baltimore, and Washington DC starting from New York."

Troubleshooting TollGuru MCP Server with Pydantic AI

Common issues when connecting TollGuru to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

TollGuru + Pydantic AI FAQ

Common questions about integrating TollGuru MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer. your TollGuru MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.