How to Use the Airwallex MCP in CrewAI

Deploy specialized financial agent teams to monitor accounts and reconcile transfers with the Airwallex integration for CrewAI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Airwallex MCP to CrewAI

Create your Vinkius account to connect Airwallex 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 Airwallex with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build autonomous treasury teams with this MCP Server

Single agents get confused when handling complex corporate finance tasks. You assign specific roles to different members of a CrewAI squad. A monitoring agent constantly runs `get_balance` to watch for low thresholds across your global accounts. When funds drop, that monitor flags the issue in shared memory. A secondary analyst agent picks up the context, runs `get_fx_rates`, and drafts a currency conversion proposal. The execution happens sequentially without a human lifting a finger.

Reconcile international wires hierarchically

Finding missing payments usually ruins an analyst's afternoon. You can configure a manager agent to delegate this exact task. The manager tells a subordinate to execute `list_payments` and cross-reference the output against internal invoices. If the subordinate spots a discrepancy, it pulls historical data using `list_transfers`. The manager reviews the compiled report and decides whether to alert the finance team or close the ticket.

Filter CrewAI tool access by agent role

You do not want your research agents touching live payment tools. Using the filter parameter in the MCP setup, you restrict exactly what each persona can do. The auditor agent gets read-only access to `list_accounts`. Meanwhile, the payee manager gets exclusive rights to `list_beneficiaries`. This strict separation of duties prevents an overzealous language model from hallucinating a wire transfer while it was supposed to be doing a routine audit.

Setup guide

Set up Airwallex 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 Airwallex tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Install the framework with the tools extra package. You can pass your Vinkius endpoint directly into the agent's server array for a quick setup.

Yes. Import the HTTP server class from the MCP module and use the filter argument. This lets you expose specific read-only tools to certain agents while hiding the rest.

You build a sequential process where one agent fetches the raw data and another analyzes it. The first pulls the transfer records, and the second compares those figures against your internal ledger using shared memory.

A manager agent can definitely delegate financial queries to subordinates. The manager assigns the account lookup task, reviews the returned data, and decides the next step based on the findings.

Beneficiary names and routing numbers never leak outside the designated query. The Vinkius platform runs your requests in ephemeral V8 isolates that vanish the moment the data returns to your application.

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