How to Use the HowLongToBeat MCP in Pydantic AI

Q: How do I register the HowLongToBeat MCP Server in pydantic-ai?

You import MCPToolset from the library, point it to the server's HTTP endpoint, and pass it to your Agent constructor in the toolsets list.

Query game completion times with strict runtime type-safety using Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect HowLongToBeat MCP to Pydantic AI

Create your Vinkius account to connect HowLongToBeat 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 HowLongToBeat with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe playtime validation in Pydantic AI

The `search_game_times` tool returns structured game duration statistics that are validated against strict Pydantic models at runtime. If the underlying data format changes, your agent raises an immediate validation error instead of passing bad data. This prevents your gaming application from crashing due to unexpected null values or broken strings. You get guaranteed integers for main story and completionist metrics, allowing you to write reliable math operations in Python.

Model-agnostic game length searches

The `search_game_times` tool works across any LLM backend you configure in Pydantic AI. Whether you use Anthropic, OpenAI, or a local model, the tool interface remains identical. This abstraction lets you swap models without rewriting your game-search logic. The agent calls the MCP server using standard tool schemas, ensuring consistent playtime data retrieval regardless of the underlying brain.

Prevent silent failures in game queries

The `search_game_times` tool integrates with Pydantic AI's unified toolset handler to catch data anomalies. If a niche game returns incomplete stats, the framework forces the agent to handle the missing fields explicitly. You avoid the classic LLM issue where the agent hallucinates a game length when the database has no record of it. The strict type validation ensures your app only displays real, verified community numbers.

Setup guide

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

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

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

You import `MCPToolset` from the library, point it to the server's HTTP endpoint, and pass it to your `Agent` constructor in the `toolsets` list.

The framework validates the response against the expected schema. If fields are missing, Pydantic AI raises a validation error, preventing your agent from processing corrupted playtime data.

Yes. The MCP client handles async execution natively, allowing your agent to run multiple `search_game_times` queries in parallel without blocking your main event loop.

Yes. Because the tool schema is standardized via MCP, any model supported by the framework can search and interpret game completion times.

The server only processes the raw string containing the game name to fetch playtime statistics. No user identifiers, session tokens, or personal data are ever sent to the public database or stored on disk.

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