How to Use the TollGuru MCP in LangChain

Q: Can I use TollGuru with LangChain for currency conversion?

Absolutely. Since calculatetollroute supports specifying multiple currencies (USD, CAD, EUR, etc.), your agent can get the toll estimate in one currency and then pass that value to a separate financial tool within the same chain for conversion.

Q: Is TollGuru better than a simple mapping API for multi-stop routes using LangChain?

Yes. While a standard mapper gives you directions, the calculatetollmultistop function gives you optimized planning data—it accounts for minimizing total toll costs across multiple waypoints, which basic routing APIs don't do.

Q: How does TollGuru integrate with LangChain’s state management?

Since the MCP Server is stateless by default, you use client.session() to maintain context. This allows your agent to remember intermediate calculations or parameters (like vehicle type) across multiple tool calls within a single session.

Build complex reasoning chains with TollGuru via LangChain.

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 LangChain

Create your Vinkius account to connect TollGuru to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Plan Multi-Stop Trips using the MCP Server

Need to figure out costs for a delivery route? Start by calling `calculate_toll_multi_stop`. This tool figures out detailed toll breakdowns and fuel expenses at every single plaza along your multi-waypoint journey. The output of this calculation immediately feeds into the next step of your chain, letting your agent continue optimizing that complex logistics plan. Because the results are structured data, you can pass them directly to a database lookup tool or another API call within the same LangChain sequence. Your agent decides when and how many times it needs to run this specific MCP Server function.

Calculate Full Trip Costs in Multi-Step Chains

The `calculate_toll_route` tool gives you a full trip cost breakdown, covering tolls, fuel, and even estimated driver time. You can set up a multi-step chain where the initial query runs this function to get baseline data. Then, another agent in your LangChain workflow takes that output—say, the list of acceptable currencies—and uses it for subsequent financial validation. This means you're not just getting an answer; you're building a process. You can chain together multiple MCP calls: first calculating the route, then using that calculated cost to decide which payment method to recommend.

Reconcile Existing Routes with TollGuru

If your mapping service already generated a polyline for a trip, don't re-route. Use `calculate_toll_from_polyline`. This tool takes that existing route data and returns the necessary toll, fuel, and cost info without changing the path. This is perfect for post-trip reconciliation in a chain. You can make your agent use this function early in the pipeline: 'Get tolls for this polyline' -> 'Compare to budget stored in vector DB' -> 'Send final report.' It keeps the flow moving with minimal friction.

Setup guide

Set up TollGuru MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes TollGuru tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "tollguru-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent TollGuru transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

The MCP Server functions are treated as links. Your agent decides which tool to call and in what order based on the intermediate results of previous steps. The output of one function becomes the direct input for the next, letting you build complex reasoning pipelines.

Absolutely. Since `calculate_toll_route` supports specifying multiple currencies (USD, CAD, EUR, etc.), your agent can get the toll estimate in one currency and then pass that value to a separate financial tool within the same chain for conversion.

This MCP Server handles route geometry (polylines), vehicle specifications, and detailed cost structures, including tolls, fuel costs, and time estimates. All of this is structured data that can be passed between nodes in your chain.

Yes. While a standard mapper gives you directions, the `calculate_toll_multi_stop` function gives you optimized planning data—it accounts for minimizing total toll costs across multiple waypoints, which basic routing APIs don't do.

Since the MCP Server is stateless by default, you use `client.session()` to maintain context. This allows your agent to remember intermediate calculations or parameters (like vehicle type) across multiple tool calls within a single session.

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