How to Use the ReferralHero MCP in Pydantic AI

Q: How do I register the ReferralHero toolset in Pydantic AI?

Use the MCPToolset class pointing to your Vinkius HTTP endpoint and pass it to the Pydantic AI Agent toolsets parameter. This unified approach handles ReferralHero schema translation and validation automatically.

Build type-safe referral workflows with Pydantic AI by validating every ReferralHero API response at runtime.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect ReferralHero MCP to Pydantic AI

Create your Vinkius account to connect ReferralHero to Pydantic AI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup ReferralHero with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Type-Safe Subscriber Management with Pydantic AI

`get_subscriber` inspects a user's referral profile while Pydantic AI guarantees the response matches your expected Python schemas. If the ReferralHero API returns unexpected fields, your agent catches the validation error immediately. When adding new signups, `add_subscriber` enforces strict type safety on subscriber emails and metadata. This prevents malformed data from corrupting your ReferralHero campaign database before the write operation occurs.

Validate Point Transactions with strict MCP Server schemas

`add_points` modifies a subscriber's referral score while Pydantic AI validates the input payload types. The framework ensures point values are strictly formatted as integers before sending the payload to the MCP Server. To track these updates, `list_transactions` pulls the ReferralHero ledger into strongly-typed Pydantic models. You build reliable dashboards knowing that zero-value or corrupt transactions will trigger loud, catchable exceptions in Pydantic AI.

Verify Rewards and Leaderboards at Runtime

`get_rewards` lists active incentives while your Pydantic AI agent parses the ReferralHero reward structures into clean, validated data objects. Your code can confidently process payout logic without worrying about missing dictionary keys. For public-facing pages, `get_leaderboard` fetches the top referrers under strict runtime guarantees. This prevents invalid ranking data from breaking your frontend when the Pydantic AI agent compiles ReferralHero leaderboard digests.

Setup guide

Set up ReferralHero 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": {
        "referralhero-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent ReferralHero 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 ReferralHero. 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 ReferralHero 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 ReferralHero MCP in Pydantic AI

Use the `MCPToolset` class pointing to your Vinkius HTTP endpoint and pass it to the Pydantic AI `Agent` toolsets parameter. This unified approach handles ReferralHero schema translation and validation automatically.

Pydantic AI raises a validation error immediately rather than letting your agent hallucinate or process corrupt ReferralHero payloads. This runtime safeguard keeps your referral logic accurate.

Yes, this setup is completely model-agnostic. You can run your ReferralHero workflows in Pydantic AI using Anthropic, Gemini, or local models while maintaining strict type-safety.

No, the MCP Server automatically exposes OpenAPI-compliant schemas. Pydantic AI reads these definitions at startup to build runtime validation models for ReferralHero on the fly.

Your referral codes and subscriber point balances are processed inside a secure, ephemeral V8 isolate on Vinkius. Pydantic AI validates these payloads in memory on your host machine, ensuring no sensitive data is leaked or stored.

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