How to Use the TollGuru MCP in LlamaIndex

Q: Can LlamaIndex use TollGuru for multi-stop route planning?

Yes. The calculatetollmultistop tool generates structured data that gets indexed. You can then query your knowledge base, not just the live API, to see optimal routes and cost savings from previous planning sessions.

Q: Do I need TollGuru for complex trip budgeting with LlamaIndex?

Not only do you. The calculatetollroute tool provides the full cost breakdown, and indexing those results lets your application maintain a historical record of budgets and actual costs for comparison.

Augment knowledge with TollGuru using LlamaIndex for grounded answers.

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 LlamaIndex

Create your Vinkius account to connect TollGuru to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Search Past Trip Costs via MCP Server

The unique power of the MCP Server is that its output becomes searchable data. When you use `calculate_toll_route`, the resulting detailed trip costs, plaza names, and currency breakdowns are indexed into a vector store. This means your LlamaIndex application can query past sessions or configurations to answer questions grounded in actual API usage. Instead of hallucinating an estimate, you ask: 'What was the total cost for LA to SF last month?' The system retrieves the stored data from the MCP Server and provides a factual answer.

Grounding Logistics Data with LlamaIndex

When planning complex deliveries, use `calculate_toll_multi_stop`. The resulting optimization suggestions—like which specific waypoint order minimizes costs—are indexed. Developers build RAG applications where live API data and documents are combined into one searchable index for logistics managers. This is better than just calling the function; you can now query the knowledge base: 'Show me all multi-stop routes over $500 in Q3.' The answer uses the stored MCP Server results.

Calculating Tolls and Costs using LlamaIndex

The `calculate_toll_from_polyline` tool provides a quick cost check for an existing route. By indexing these calculations, your knowledge base can answer questions like: 'Based on our historical GPS data, what were the toll costs between points A and B?' The MCP Server output gives you factual answers immediately. This turns raw API calls into actionable corporate knowledge, allowing users to query massive amounts of trip data without running a new calculation every time.

Setup guide

Set up TollGuru MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all TollGuru MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to TollGuru tools.",
)
response = await agent.run("List recent TollGuru data")

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 LlamaIndex

It indexes the detailed results from the MCP Server—like plaza names and specific costs—into your vector store. This lets you query past API calls semantically, so you can ask complex questions like 'What was my cost breakdown for the Chicago to Detroit run?'

Yes. The `calculate_toll_multi_stop` tool generates structured data that gets indexed. You can then query your knowledge base, not just the live API, to see optimal routes and cost savings from previous planning sessions.

The server touches structured data concerning route geometry (polylines), vehicle specifications, and detailed financial metrics including tolls, fuel costs, and time estimates. This is all stored as queryable knowledge.

Not only do you. The `calculate_toll_route` tool provides the full cost breakdown, and indexing those results lets your application maintain a historical record of budgets and actual costs for comparison.

The server touches route geometry (polylines), vehicle specifications, and detailed cost structures. Because the output is indexed into a private knowledge base, you maintain control over which specific trip details are searchable.

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