How to Use the Arrivy MCP in CrewAI

Deploy an autonomous field service team using CrewAI. Your agents collaborate to manage Arrivy bookings, dispatch, and monitoring 24/7.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Arrivy MCP to CrewAI

Create your Vinkius account to connect Arrivy to CrewAI 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 Arrivy with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Assemble a booking and scheduling crew

With CrewAI, you can assign specialized roles to different agents. Create a 'Booking Agent' that uses the `create_customer` tool and a 'Scheduling Agent' that uses `create_task`. They can work together, sharing information through CrewAI's shared memory to process new job requests. Another agent, the 'Verification Specialist', could use `list_customers` to prevent duplicates before the Booking Agent acts. This divides the labor, letting each agent focus on one part of the problem, which is how CrewAI builds complex autonomous systems.

Run a fully autonomous dispatch operation

Build a 'Dispatch Crew' to manage your field operations. A 'Lookout Agent' can periodically run `list_tasks` to find unassigned jobs. It passes these jobs to a 'Dispatcher Agent', which then uses `list_crews` to find available personnel and `update_task` to make the assignment. This isn't just a script; it's a team of agents coordinating. You can even add a 'Notification Agent' that messages the customer after the `update_task` tool is successfully called. This MCP server gives your crew the specific actions they need to run your business.

Use an agent crew to monitor Arrivy health

You can dedicate a simple CrewAI crew to system monitoring. One agent's only job is to run `get_account_check` every few minutes. If it fails, it passes a work item to an 'Escalation Agent' that notifies an administrator. This is a perfect example of using an MCP server for autonomous oversight. Your crew becomes a reliable, always-on monitor for your connection to Arrivy. It's a simple, powerful way to ensure your operations are never down because of a dropped connection.

Setup guide

Set up Arrivy 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 Arrivy tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

task = Task(
    description="List recent Arrivy 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="Arrivy Analyst",
        goal="Access and analyze Arrivy data via MCP.",
        backstory="Expert analyst with direct Arrivy access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Arrivy 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 Arrivy. 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 Arrivy 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 Arrivy MCP in CrewAI

Assign roles. Create one agent to handle customer creation with `create_customer` and another to schedule the job with `create_task`. They can work sequentially, with the first agent passing the new customer ID to the second, all managed by CrewAI's process.

Yes, that's a perfect use case. Set up a 'Dispatcher' agent that uses `list_tasks` to find work, `list_crews` to find people, and `update_task` to assign the job. You can run this crew on a schedule to continuously clear your unassigned queue.

When configuring your agents in CrewAI, you can pass a filtered list of tools to each one. This lets you create specialized agents. For example, a 'Billing' agent might only have access to read-only tools, while a 'Dispatcher' agent can use `update_task`.

Absolutely. Create a simple, two-agent crew. The first agent's sole purpose is to periodically run the `get_account_check` tool from this MCP. If it ever fails, it tasks the second agent to send an alert.

Your data is handled in a secure, isolated environment. Vinkius runs the Arrivy MCP Server inside a V8 Isolate sandbox for each request. This means your data, including customer details, crew info, and task specifics, is only present for the duration of the tool execution and is never stored on the server.

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