How to Use the TollGuru MCP in CrewAI

Autonomous toll cost intelligence for your operations crew with CrewAI and TollGuru Alternative MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect TollGuru MCP to CrewAI

Create your Vinkius account to connect TollGuru to CrewAI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup TollGuru with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Determine tolls from addresses

Assign a specialized agent to the task of calculating costs. The agent uses `calculate_tolls_by_address` to get fuel estimates for trips between two defined points, supporting multi-vehicle types. This is a clean, contained operation. The crew can be set up where Agent A finds the addresses, and Agent B calculates the cost using this tool, ensuring separation of duties and clear action logging.

Analyze encoded routes or GPS tracks

For post-trip billing, use a specialized agent with `calculate_tolls_by_gps` or `calculate_tolls_by_polyline`. The shared memory allows the team to pass raw data (like a polyline) from the research phase directly into the analysis phase. This eliminates human intervention in complex data transfers. A monitor agent watches the data flow, ensuring the correct tool is called with accurate inputs.

Verify toll rates and usage counts

Create a specialized 'Billing Agent' whose sole job is checking costs. It uses `get_toll_rates` for specific lookups or `get_transaction_count` to monitor account status before any calculation runs. This adds an essential pre-check step. The crew can enforce that the usage count must be checked *before* running a trip calculation, making the entire operation self-correcting.

Setup guide

Set up TollGuru MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke TollGuru tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="TollGuru Analyst",
    goal="Access and analyze TollGuru data via MCP.",
    backstory="Expert analyst with direct TollGuru access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent TollGuru transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="TollGuru Analyst",
        goal="Access and analyze TollGuru data via MCP.",
        backstory="Expert analyst with direct TollGuru access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent TollGuru transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

You assign specialized agents: one researches addresses for `calculate_tolls_by_address`, another calculates the cost, and a third verifies rates with `get_toll_rates`. This collaborative structure makes the process robust.

Yes. You can give a dedicated agent the job of processing trip logs, calling `calculate_tolls_by_gps`. The output is then passed to another agent for final cost reporting.

You set up a monitoring agent specifically tasked with calling `get_transaction_count` at the start of every session. If the count is too high, the moderator agent can halt the entire crew operation.

It’s great. You let one agent submit an encoded polyline to `calculate_tolls_by_polyline`, and a separate analyzing agent takes that output to format the final, comprehensive bill.

The server handles varied geo-spatial inputs—addresses, coordinates, polylines, and raw GPS tracks. The crew's shared memory ensures these diverse data types are passed accurately between specialized agents.

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