How do I get my API Keys for Friendbuy?

Log in to your Friendbuy account, go to Settings > Developer, and you will find your Access Key and Secret Key.

Can I manually log a purchase through the agent?

Yes! Use the 'track_conversion_purchase' tool. Provide the Order ID, amount, and customer email. If you include the 'referralCode', it will trigger the advocate's reward.

How do I verify if a referral code is still valid?

Use the 'get_referral_code_status' tool. The agent will check the Developer API and return the active status and associated reward value.

Is it possible to list webhooks?

Yes, the 'list_webhooks' tool retrieves all active webhook configurations so you can verify where real-time reward notifications are being sent.

Friendbuy MCP Server for Pydantic AI 8 tools — connect in under 2 minutes

Name: Friendbuy
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 8 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Friendbuy through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Friendbuy "
            "(8 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Friendbuy?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Friendbuy MCP Server

Connect your Friendbuy account to any AI agent to automate your referral programs and customer loyalty workflows through the Model Context Protocol (MCP). Friendbuy is a high-growth referral marketing platform that powers word-of-mouth campaigns for leading brands. This MCP server enables you to track referral events, log conversions, and retrieve reward distributions directly through natural conversation.

Pydantic AI validates every Friendbuy tool response against typed schemas, catching data inconsistencies at build time. Connect 8 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.

Key Features

Referral Rewards Tracking — List all distributed referral rewards and filter them by advocate to understand who your top promoters are.
Conversion Logging — Post purchase and signup events programmatically to trigger the referral reward lifecycle.
Code Generation & Verification — Create personal referral codes for customers and check their active statuses instantly.
Purchase History — Retrieve a list of all tracked purchases that have been attributed to referral campaigns.
Webhook Monitoring — List configured webhooks to ensure your internal systems are receiving real-time reward notifications.
API Health Checks — Verify your connection to both the Merchant API and Developer API v2 environments seamlessly.

The Friendbuy MCP Server exposes 8 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Friendbuy to Pydantic AI via MCP

Follow these steps to integrate the Friendbuy MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 8 tools from Friendbuy with type-safe schemas

Why Use Pydantic AI with the Friendbuy MCP Server

Pydantic AI provides unique advantages when paired with Friendbuy through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your Friendbuy integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Friendbuy connection logic from agent behavior for testable, maintainable code

Friendbuy + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Friendbuy MCP Server delivers measurable value.

Type-safe data pipelines: query Friendbuy with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Friendbuy tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Friendbuy and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Friendbuy responses and write comprehensive agent tests

Friendbuy MCP Tools for Pydantic AI (8)

These 8 tools become available when you connect Friendbuy to Pydantic AI via MCP:

check_api_connection

Verify API access

create_referral_code

Generate share code

get_referral_code_status

Check code status

list_referral_rewards

List awarded referrals

list_tracked_purchases

List tracked purchases

list_webhooks

List webhook configs

track_conversion_purchase

Log a purchase

track_conversion_signup

Log a signup

Example Prompts for Friendbuy in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Friendbuy immediately.

"List all recent referral rewards distributed."

"Generate a new referral code for customer 'user_123' (jane@email.com)."

"Track a $50 purchase for order 'ORD-987' from 'friend@email.com' using code 'JANE-REF-99'."

Troubleshooting Friendbuy MCP Server with Pydantic AI

Common issues when connecting Friendbuy to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Friendbuy + Pydantic AI FAQ

Common questions about integrating Friendbuy MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer. your Friendbuy MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.