How to Use the Checkout.com MCP in CrewAI

Q: How would a CrewAI team use voidpayment vs refundpayment with Checkout.com?

An 'Order Agent' could authorize a payment with requestpayment. If a 'Warehouse Agent' reports the item is out of stock before capture, the Order Agent would use voidpayment. If the report comes after capture, a 'Returns Agent' would have to use refundpayment.

Deploy an autonomous finance team on CrewAI to manage your Checkout.com payments, refunds, and customer instruments 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 Checkout.com MCP to CrewAI

Create your Vinkius account to connect Checkout.com 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 Checkout.com with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Assign Payment Operations to Specialized Agents

Create a 'Billing Agent' that uses `request_payment` to charge customers and a 'Fulfillment Agent' that uses `capture_payment` only after an order ships. The agents share context but have separate roles. This separation of duties is CrewAI's strength. You can build a reliable, autonomous system where one agent handles authorizations and another handles settlements, reducing the chance of errors.

Build a Crew for Proactive Account Management

A 'Compliance Agent' can use `get_instrument` to periodically check for expiring cards. When it finds one, it passes the task to a 'Communications Agent' to notify the customer. Meanwhile, a 'Cleanup Agent' can use `delete_instrument` to purge old, inactive payment methods based on your business rules. This entire process runs automatically with your CrewAI team and this MCP Server.

Automate Reconciliation with a CrewAI MCP Server

Set up an 'Auditor Agent' to run daily. It uses `get_payment_details` and `get_payment_actions` to pull transaction data from Checkout.com. It then passes this data to an 'Analyst Agent' that compares it against your internal order database, flagging any discrepancies for a human to review. This turns a manual, error-prone task into a daily, autonomous check.

Setup guide

Set up Checkout.com 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 Checkout.com tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

The simplest way is to pass your Vinkius MCP Server URL directly into the `mcps` list when defining your Agent in Python. For more control, use `MCPServerHTTP` from `crewai.mcp` to filter which tools each agent can access.

Yes. You could have a 'Support Agent' that logs a refund request, which then gets passed to a 'Finance Agent' that executes the `refund_payment` tool. This creates a clear, auditable workflow for handling customer refunds through Checkout.com.

Yes, the system is designed for security. Vinkius provides a single authentication token for your MCP endpoint. Each agent's request is processed in an isolated, zero-trust sandbox that is destroyed after the operation completes.

An 'Order Agent' could authorize a payment with `request_payment`. If a 'Warehouse Agent' reports the item is out of stock before capture, the Order Agent would use `void_payment`. If the report comes after capture, a 'Returns Agent' would have to use `refund_payment`.

The agents work with transaction IDs and instrument tokens from your Checkout.com account, not raw card numbers. Every tool call from CrewAI to the MCP server is an atomic, stateless operation authenticated by your private token and executed in a dedicated, ephemeral V8 sandbox.

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