How to Use the ReferralCandy MCP in Pydantic AI

Q: How do I initialize the ReferralCandy MCP Server in Pydantic AI?

You use the MCPToolset constructor pointing to your Vinkius HTTP endpoint. Pass this toolset directly into your agent's toolsets list, and the framework handles the rest.

Q: Can I use Pydantic AI to register a ReferralCandy purchase safely?

Yes, you can call registerpurchase within your agent's execution loop. The inputs are strictly typed, ensuring you never send malformed purchase amounts or invalid referral codes to the API.

Build type-safe referral workflows with Pydantic AI and ensure every ReferralCandy API response matches your exact schemas.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect ReferralCandy MCP to Pydantic AI

Create your Vinkius account to connect ReferralCandy 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 ReferralCandy with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Validate ReferralCandy payloads using Pydantic AI

The `get_referral` tool fetches detailed referral transaction records, which Pydantic AI immediately validates against strict runtime types. If the API structure changes or returns unexpected null values, your code raises an error instantly instead of failing silently downstream. This MCP integration ensures your financial and marketing pipelines stay robust. You can trust that the data your agent processes matches your internal database models exactly.

Audit pending rewards with absolute type safety

The `list_pending_rewards` tool retrieves all outstanding payouts waiting for approval. Your agent can parse this list, run `list_rewards` to cross-reference historical payouts, and flag any discrepancies before you release funds. Because every field is type-checked at the boundary, you don't have to write defensive try-except blocks. Your agent operates with clean, validated Python objects.

Track referred purchases via MCP Server

The `list_purchases` tool lets your agent monitor which sales came from referral links. It can filter these records using `list_referrals_by_period` to generate weekly reports on campaign ROI. This gives your team reliable attribution data. Your agent can compile these numbers into clean markdown summaries without worrying about malformed API payloads breaking the loop.

Setup guide

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

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

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

You use the `MCPToolset` constructor pointing to your Vinkius HTTP endpoint. Pass this toolset directly into your agent's toolsets list, and the framework handles the rest.

The framework will raise a validation error immediately. This prevents your agent from making decisions based on corrupted or incomplete customer profiles.

Yes, you can call `register_purchase` within your agent's execution loop. The inputs are strictly typed, ensuring you never send malformed purchase amounts or invalid referral codes to the API.

Yes, the toolset integration handles async calls out of the box. Your agent can fetch multiple campaigns or advocate profiles concurrently without blocking your main event loop.

Your credentials are encrypted and managed entirely by Vinkius. The MCP Server only accesses advocate emails and purchase totals during active tool execution, running inside a zero-trust, ephemeral sandbox.

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