How to Use the Friendbuy MCP in Pydantic AI

Q: How do I connect the Friendbuy MCP Server to Pydantic AI?

Install pydantic-ai-slimmcp. Initialize the MCPToolset with your HTTP endpoint URL. Pass this toolset into your Agent constructor. The legacy MCPServerHTTP method is deprecated.

Q: How do Friendbuy and Pydantic AI handle missing reward data?

If listreferralrewards returns an unexpected null value, the framework raises a runtime error. Your agent will not attempt to process incomplete attribution records.

Integrate the Friendbuy MCP Server with Pydantic AI for type-safe referral tracking. Your agent validates every conversion payload before execution.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Friendbuy MCP to Pydantic AI

Create your Vinkius account to connect Friendbuy 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 Friendbuy with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe conversion logging

`track_conversion_purchase` logs revenue events into your attribution system. Pydantic AI enforces strict schema validation on the request. If your application tries to pass a string instead of an integer for the order total, the framework throws a validation error immediately. No silent failures. The same strictness applies to `track_conversion_signup`. Your agent constructs the customer data payload, and Pydantic verifies the email formats and required IDs. You get absolute certainty that your marketing metrics reflect reality.

Audit rewards with the Pydantic AI framework

`list_referral_rewards` returns the historical payout data for your campaigns. Your agent parses this array into strongly typed Python objects. It compares these objects against `list_tracked_purchases` to ensure every payout maps to a valid, completed transaction. You catch API drift instantly. If the upstream provider changes their response structure, Pydantic AI catches the mismatch. Your agent stops execution rather than hallucinating missing fields or corrupting your database.

Manage codes and webhooks via this MCP Server

`create_referral_code` generates unique identifiers for your marketing campaigns. The agent immediately calls `get_referral_code_status` to verify the asset. Every state change maps to a defined schema, eliminating guesswork around active versus inactive codes. You maintain visibility into your event pipeline. The agent queries `list_webhooks` to confirm your endpoints are registered. It runs `check_api_connection` as a health check before executing high-stakes batch operations.

Setup guide

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

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

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

Install `pydantic-ai-slim[mcp]`. Initialize the `MCPToolset` with your HTTP endpoint URL. Pass this toolset into your Agent constructor. The legacy `MCPServerHTTP` method is deprecated.

Yes. The framework validates all inputs against the defined schemas for tools like `track_conversion_purchase`. If the data types mismatch, it blocks the API call.

You can. Pydantic AI is model-agnostic. You can route the tool execution through local models, Anthropic, or OpenAI, while maintaining the exact same validation logic.

If `list_referral_rewards` returns an unexpected null value, the framework raises a runtime error. Your agent will not attempt to process incomplete attribution records.

The server transmits personally identifiable information and order values. Pydantic AI ensures this data stays within your local execution environment. Your schema definitions govern exactly what fields the agent can read or write.

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