How to Use the Hyperswitch MCP in Pydantic AI

Q: How do I register the Hyperswitch MCP server in pydantic-ai?

Use the MCPToolset class pointing to your Vinkius HTTP endpoint. Pass the toolset instance into your Agent constructor within the toolsets list to enable immediate, validated payment tools.

Q: What happens if Hyperswitch returns a payload that doesn't match the pydantic-ai schema?

Your pydantic-ai agent will raise a validation error immediately. This loud failure prevents downstream code from executing with corrupt transaction or payout data, protecting your ledger from errors.

Enforce strict runtime validation on your Hyperswitch payments and payouts using type-safe Pydantic AI agents and MCP 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 Pydantic AI

Create your Vinkius account to connect Hyperswitch to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe payment lookups with Pydantic AI

Never worry about unexpected API changes breaking your checkout flows. When your Pydantic AI agent calls `get_payment` or `list_payments`, the response is immediately validated against strict Python type models before your agent can act on it. If a payment processor returns a malformed status or an unexpected null value, the framework catches it instantly. This prevents your agent from hallucinating transaction states or executing incorrect business logic based on bad data.

Strict customer profile validation via MCP Server

Managing customer accounts requires absolute data integrity. This MCP Server allows your agent to pull verified data using `get_customer` and `list_customers` with zero risk of silent corruption. The incoming customer payloads are parsed directly into Pydantic models. Your agent can confidently read email addresses, metadata, and payment histories without manual validation code, making customer verification perfectly reliable.

Validated refund tracking

Refund processing leaves no room for error. Your agent uses `get_refund` and `list_refunds` to track where returned money is landing across your payment processors. Because every refund schema is strictly typed, the agent can safely compare refund amounts against the original transaction records. Any data mismatch triggers an immediate validation exception, stopping bad refund logic in its tracks.

Setup guide

Set up Hyperswitch MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "hyperswitch-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Hyperswitch tools.",
)

result = await agent.run("List recent Hyperswitch transactions")
print(result.output)

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 Pydantic AI

Use the `MCPToolset` class pointing to your Vinkius HTTP endpoint. Pass the toolset instance into your `Agent` constructor within the `toolsets` list to enable immediate, validated payment tools.

Your `pydantic-ai` agent will raise a validation error immediately. This loud failure prevents downstream code from executing with corrupt transaction or payout data, protecting your ledger from errors.

Yes, you can connect using either Streamable HTTP or SSE transports. Simply configure your Vinkius endpoint URL inside the `MCPToolset` initialization block to start validating payment data.

Yes, this setup is completely model-agnostic. You can run your agent on Ollama or any local LLM, and the framework will still enforce strict schema validation on tools like `list_payouts`.

All payouts and transaction records are processed through Vinkius's isolated V8 sandboxes. Your API keys are never exposed to the agent framework, and all data transfers are encrypted end-to-end to maintain PCI compliance.

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