How to Use the Bonusly MCP in Pydantic AI

Enforce strict types on Bonusly responses with Pydantic AI for reliable agent behavior without silent failures.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Bonusly MCP to Pydantic AI

Create your Vinkius account to connect Bonusly 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 Bonusly with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Bonusly data in Pydantic AI

Every response from `get_my_profile` or `list_users` undergoes immediate validation against your Pydantic models. If the API structure changes, your agent crashes safely rather than hallucinating fields. This approach gives you total confidence in the data your agent processes. You define the shape of the bonus records, and the framework ensures the reality matches your code.

Manage recognition tasks with Pydantic AI

Integrate `give_bonus` into your agent's workflow using a type-safe interface. You define the expected input types, and the framework catches errors before they reach the network. This prevents malformed requests from being sent to your team's account. It keeps your recognition logs clean and accurate.

Handle redemptions with Pydantic AI

Run `list_redemptions` to audit rewards and map them to your internal accounting structures. The framework forces you to define how this data looks, preventing runtime surprises. You get a predictable flow of information that integrates perfectly with your existing Python logic. It turns raw API responses into structured objects.

Setup guide

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

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

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

Use the MCPToolset class to connect your server URL. Once configured, you add the toolset to your agent instance to start executing commands.

Your agent will raise a validation error immediately. This stops the execution and prevents corrupted data from polluting your agent's state.

Yes, you must have the server running externally. The framework connects via SSE or Streamable HTTP to bridge your agent with the tools.

Absolutely. Because this is model-agnostic, you can swap between local models and hosted ones without changing how you interact with the MCP tools.

We use memory-safe serialization for all data transfers. Your sensitive redemption logs are only held in volatile memory for the duration of the agent's task.

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