How to Use the Bored MCP in Pydantic AI

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

Use the unified MCPToolset constructor with your Vinkius HTTP URL. Pass that toolset instance directly into your Agent configuration to expose the activity tools.

Get type-safe Bored suggestions in Pydantic AI with strict runtime validation of every activity.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Bored MCP to Pydantic AI

Create your Vinkius account to connect Bored 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 Bored with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Bored searches with Pydantic AI models

The `find_activity` tool lets your Pydantic AI agent search for things to do using strict parameter validation. If the Bored server returns a price or accessibility rating that violates your schema, the framework catches it instantly. This prevents malformed data from corrupting your application state. You get clean, validated JSON objects that match your exact type definitions.

Fetch Bored keys using type-safe MCP Server tools

The `get_activity_by_key` tool retrieves specific activities while ensuring the key format matches your internal Pydantic schemas. By using the unified `MCPToolset` class, you connect directly to the external Vinkius server. If the returned payload contains unexpected fields, the agent fails loudly rather than silently passing bad data to your LLM. This guarantees your application logic remains predictable.

Ensure clean data from random Bored activity lookups

The `get_random_activity` tool provides a spontaneous suggestion that is immediately parsed into a typed Pydantic model. Your agent can confidently use fields like category and price because they are checked at runtime. This setup works across any model provider you choose. You can run Anthropic, OpenAI, or local models while keeping the incoming activity data fully structured.

Setup guide

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

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

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

Use the unified `MCPToolset` constructor with your Vinkius HTTP URL. Pass that toolset instance directly into your `Agent` configuration to expose the activity tools.

The framework will raise a validation error immediately. This prevents silent failures and ensures your agent never processes corrupt activity formats.

Yes, this framework is model-agnostic. You can run the Bored tools with local LLMs, OpenAI, or Anthropic while keeping the same type-safety guarantees.

No, that class is deprecated in Pydantic AI. You should use the unified `MCPToolset` class to connect to the Bored MCP Server hosted on Vinkius.

No, the Bored server only receives raw argument values like price thresholds or participant numbers. Your custom Pydantic schemas and validation logic remain entirely local to your application.

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