How to Use the Mastercard MCP in AutoGen

Q: How can I create an AutoGen agent that only uses the Mastercard submitfraudreport tool?

When you instantiate your AssistantAgent, you pass a specific list of tools to its constructor. To create a specialized agent, just give it a list containing only the submitfraudreport tool function. It won't know the others exist.

Q: Can I have two AutoGen agents debate the output of the Mastercard validateaccount tool?

Absolutely. One agent can call validateaccount and present the "VALID" status. A second, more skeptical agent could then challenge that, perhaps asking for more context or suggesting a second validation step. This debate is the core of AutoGen.

Q: What's a good agent setup in AutoGen for analyzing merchant data from the Mastercard MCP server?

A simple but effective setup is a two-agent group. A UserProxyAgent executes the code, and an AssistantAgent has access to tools like searchmerchants and getmerchant. The assistant plans the analysis, and the proxy agent runs the tool calls and reports back the data.

Q: Does the AutoGen adapter automatically generate function definitions for the Mastercard tools?

Yes. The mcpservertools function connects to the MCP server, inspects the available tools, and prepares them for use by AutoGen agents. You get a list of ready-to-use Python functions without writing boilerplate code.

Build teams of AI agents that debate and solve complex financial problems with AutoGen and Mastercard APIs.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mastercard MCP to AutoGen

Create your Vinkius account to connect Mastercard to AutoGen 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 Mastercard with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Create a Multi-Agent Fraud Council

A single agent making a fraud decision is a liability. Use AutoGen to create a team. One agent, the "Scout," uses `bin_lookup` and `get_merchant` to gather facts about a transaction. It presents its findings to the group. A second agent, the "Analyst," debates the evidence, looking for patterns. A third "Compliance" agent ensures the criteria for using `submit_fraud_report` are met before giving the final approval. This conversational approach reduces errors and creates an auditable decision-making trail.

Let Agents Plan a Business Expansion

Where should you open your next location? Task a team of AutoGen agents with finding the answer. The "Market Analyst" agent uses `search_merchants` with various `merchant_category_codes` to map existing business density and identify gaps. Meanwhile, a "Logistics" agent uses `nearby_locations` to analyze local infrastructure. The agents debate the pros and cons of different sites, challenging each other's assumptions and data. The final output isn't just a location; it's a reasoned argument backed by Mastercard data.

Your AutoGen MCP Server for Payments

Model a real-world team with AutoGen. A "Support" agent receives a user request. If it's about a specific charge, it hands off the task to a "Payments" agent, which is authorized to use the `get_merchant` tool. If the request is about finding a location, the "Support" agent can delegate to a "Navigator" agent that uses `search_places`. This specialization and conversational hand-off is what makes AutoGen powerful. Each agent has access to a specific subset of tools from this MCP server, just like a real team.

Setup guide

Set up Mastercard MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Mastercard tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

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

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Mastercard_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Mastercard data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

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

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Mastercard_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Mastercard data")
    print(result.messages[-1].content)

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 Mastercard. 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 Mastercard 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 Mastercard MCP in AutoGen

When you instantiate your `AssistantAgent`, you pass a specific list of tools to its constructor. To create a specialized agent, just give it a list containing only the `submit_fraud_report` tool function. It won't know the others exist.

Absolutely. One agent can call `validate_account` and present the "VALID" status. A second, more skeptical agent could then challenge that, perhaps asking for more context or suggesting a second validation step. This debate is the core of AutoGen.

A simple but effective setup is a two-agent group. A `UserProxyAgent` executes the code, and an `AssistantAgent` has access to tools like `search_merchants` and `get_merchant`. The assistant plans the analysis, and the proxy agent runs the tool calls and reports back the data.

Yes. The `mcp_server_tools` function connects to the MCP server, inspects the available tools, and prepares them for use by AutoGen agents. You get a list of ready-to-use Python functions without writing boilerplate code.

The server itself is stateless. The risk is in your agent conversation history. A tool like `submit_fraud_report` handles sensitive `accountNumber` and `transactionAmount` data. It's critical to configure your AutoGen environment so that logs containing this data are properly secured or redacted, as the conversation history can contain raw tool inputs.

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