How to Use the HowLongToBeat MCP in Claude Code

Q: How do I get HowLongToBeat data into a shell script with Claude Code?

You can pipe the output. For example, echo "Baldur's Gate 3" claude code "what's the playtime?" will use the piped text as context. The tool's JSON output can then be piped into tools like jq.

Q: How do I connect Claude Code to the HowLongToBeat MCP server?

Run claude mcp add --transport http howlongtobeat -- in your terminal. You only have to do this once. The configuration is saved in /.claude.json.

Pipe game completion times into any script. A HowLongToBeat server for your terminal, powered by Claude Code.

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 Claude Code

Create your Vinkius account to connect HowLongToBeat to Claude Code 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 Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Check Game Times from the CLI

This is data retrieval at its simplest. Run `claude code "how long to beat Cyberpunk 2077?"` in your terminal. That's it. Your agent connects to the HowLongToBeat MCP server, calls the `search_game_times` tool, and prints the result directly to standard output. It's fast, scriptable, and you never have to open a browser.

Automate Newsletters and Reports

Here's where the CLI proves its worth. Write a shell script that pulls a list of new game releases. Then, pipe each title to Claude Code to get its playtime via `search_game_times`. The output can be formatted for a weekly email, a Discord bot announcement, or a markdown report. Set it up in a cron job and you have a fully automated content pipeline.

Power Bots and CI/CD Pipelines

Integrate game time lookups into any backend service. A Discord bot can use a shell command to invoke Claude Code, which in turn calls this MCP server to answer user queries like `!hltb The Witcher 3`. Or, add it to a CI check. You can write a script that validates a list of game data in your repo, ensuring every entry has a valid completion time by checking it against the `search_game_times` tool.

Setup guide

Set up HowLongToBeat MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see howlongtobeat-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest HowLongToBeat transactions." It will automatically discover and invoke the available HowLongToBeat tools.

Terminal

claude mcp add --transport http howlongtobeat-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the HowLongToBeat MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "howlongtobeat-mcp": {
      "type": "url",
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Claude Code

You can pipe the output. For example, `echo "Baldur's Gate 3" | claude code "what's the playtime?"` will use the piped text as context. The tool's JSON output can then be piped into tools like `jq`.

Run `claude mcp add --transport http howlongtobeat -- ` in your terminal. You only have to do this once. The configuration is saved in `~/.claude.json`.

Absolutely. Since Claude Code is a CLI, you can install it in a workflow runner and call the `search_game_times` tool as part of any job. It's ideal for automated data validation.

It returns a clean JSON object containing the game's title and the hours for different playstyles like 'Main Story' and 'Completionist'. This makes it easy to parse in any script.

The server only receives the game title you're querying. All requests run through Vinkius's ephemeral sandboxes, which are designed for zero-trust environments like CI/CD. No secrets or session data are left behind.

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