How to Use the Hyperswitch MCP in AutoGen

Q: How do I register Hyperswitch tools with AutoGen agents?

Use the autogen-extmcp package to fetch tools from your Vinkius server. Pass the resulting tool definitions directly to the AssistantAgent constructor to let your agents invoke them.

Q: How do AutoGen agents coordinate when calling Hyperswitch APIs?

They operate in a GroupChat. One agent calls listpayments to locate an order, and another agent takes that ID to run getcustomer and verify the buyer.

Let AutoGen agents debate payment routing, dispute responses, and payout verification using Hyperswitch tools.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Hyperswitch MCP to AutoGen

Create your Vinkius account to connect Hyperswitch 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 Hyperswitch with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Resolve payouts using AutoGen agents

AutoGen lets you build a multi-agent system where different agents handle different parts of your finance pipeline. One agent can pull transaction logs using `list_payouts`, while a security agent reviews the details via `get_payout` using our MCP Server. Before any money moves, the agents debate the transaction safety in a shared chat. If the security agent flags a risk, it halts the process, avoiding costly payout errors without requiring constant human oversight.

Automated dispute resolution loops

Let your agents fight chargebacks. A monitoring agent uses `list_disputes` to catch new challenges, while a researcher agent calls `get_customer` and `list_payments` using the Hyperswitch MCP integration. A third agent reviews the collected evidence against the requirements from `get_dispute`. They negotiate the best response strategy, ensuring you submit highly defensible evidence to your payment processors.

Real-time refund verification

When a customer requests a refund, your AutoGen agents spring into action. A customer service agent looks up the transaction using `get_payment`, while a compliance agent checks refund limits with `list_refunds` and `get_refund`. They cross-reference the data to ensure the refund amount matches the original charge and doesn't violate your terms. Once they reach a consensus, the system approves the transaction with zero manual delay.

Setup guide

Set up Hyperswitch 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 Hyperswitch 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="Hyperswitch_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Hyperswitch 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="Hyperswitch_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Hyperswitch 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 Hyperswitch. 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 Hyperswitch 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 Hyperswitch MCP in AutoGen

Use the autogen-ext[mcp] package to fetch tools from your Vinkius server. Pass the resulting tool definitions directly to the AssistantAgent constructor to let your agents invoke them.

Yes. If authorized, an agent can check the transaction history with get_payment, verify eligibility via list_refunds, and run get_refund to confirm the status.

They operate in a GroupChat. One agent calls list_payments to locate an order, and another agent takes that ID to run get_customer and verify the buyer.

The executing agent receives the raw API error. It shares the failure with the group chat, allowing a recovery agent to suggest alternative steps like list_refunds.

Yes. All API payloads containing customer profiles, dispute details, and payouts are processed inside a secure, ephemeral MCP sandbox. Your API keys and payment records remain completely private.

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