How to Use the HowLongToBeat MCP in Mastra AI

Q: How can my Mastra AI agent handle cases where HowLongToBeat doesn't find a game?

Your Mastra AI workflow can check if the searchgametimes tool returns an error or empty result. If it does, you can branch the logic to try a different spelling or log the name for manual checking.

Q: Can I use Mastra AI to build a Discord bot that reports HowLongToBeat times?

Absolutely. Your agent can listen for a command like !hltb "Cyberpunk 2077", call the searchgametimes tool via this MCP server, and post the results back to the channel. Mastra's engine ensures the bot stays running.

Q: How do I set up my Mastra AI agent to use the HowLongToBeat MCP server?

In your MCPClient configuration, add this server's Vinkius URL. Your agent can then call mcpClient.listTools() to see the searchgametimes tool and use it in its workflows.

Q: Can I require human approval before my agent acts on game time data?

Yes. Mastra AI supports requireToolApproval. You could have an agent find game times and then wait for a human to confirm before, for example, publishing an article based on that data.

Q: What data privacy policies apply to my searches?

The server only processes the game titles sent in your searchgametimes requests. We don't log the searches against your account, and the ephemeral design of the Vinkius platform means the request data is gone once the job is done.

Build resilient backend agents with Mastra AI that can reliably fetch game completion times from HowLongToBeat.

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 Mastra AI

Create your Vinkius account to connect HowLongToBeat to Mastra 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Content Enrichment

Use the `search_game_times` tool to automatically add completion times to your game database. A Mastra AI agent can run on a schedule, find games missing this data, and call the tool to fill in the blanks. Because Mastra has built-in retry logic, you don't have to worry about transient network errors. If a lookup fails, your agent will automatically try again. It's a set-and-forget workflow for keeping your data fresh.

Conditional Workflow Logic

What if `search_game_times` doesn't find a match? With Mastra AI, you can build conditional logic around the tool's output. If a game isn't found, your agent can flag it for manual review or try searching with an alternate title. This turns a simple data lookup into an intelligent process. You define a chain of actions: try primary title, if fail, try alternate, if fail, log to a spreadsheet. This MCP Server gives you the data point; Mastra gives you the workflow.

Your Mastra AI MCP Server

This isn't just a generic API. It's an MCP Server built for agentic workflows. Mastra AI's client can discover and call `search_game_times` as part of a larger, multi-step process. For example, an agent could check a new game's price from one server, get its playtime from this one, and then decide if it's a good value-per-hour to recommend. Mastra connects the dots between MCP tools.

Setup guide

Set up HowLongToBeat MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All HowLongToBeat tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "howlongtobeat-mcp-client",
  servers: {
    "howlongtobeat-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "HowLongToBeat Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to HowLongToBeat tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent HowLongToBeat transactions"
);
console.log(result.text);

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 Mastra AI

Your Mastra AI workflow can check if the `search_game_times` tool returns an error or empty result. If it does, you can branch the logic to try a different spelling or log the name for manual checking.

Absolutely. Your agent can listen for a command like `!hltb "Cyberpunk 2077"`, call the `search_game_times` tool via this MCP server, and post the results back to the channel. Mastra's engine ensures the bot stays running.

In your `MCPClient` configuration, add this server's Vinkius URL. Your agent can then call `mcpClient.listTools()` to see the `search_game_times` tool and use it in its workflows.

Yes. Mastra AI supports `requireToolApproval`. You could have an agent find game times and then wait for a human to confirm before, for example, publishing an article based on that data.

The server only processes the game titles sent in your `search_game_times` requests. We don't log the searches against your account, and the ephemeral design of the Vinkius platform means the request data is gone once the job is done.

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