How to Use the HowLongToBeat MCP in CrewAI

Q: How can a CrewAI team use HowLongToBeat data to write a blog post?

A 'Researcher' agent can use searchgametimes to gather data on 10 games. A 'Writer' agent then takes this data from the crew's shared memory and drafts an article, like '10 Great Games You Can Beat in a Weekend.'

Q: What's the easiest way to give my CrewAI agents access to the HowLongToBeat server?

Just pass the Vinkius MCP server URL into the mcps list when you define your Agent in Python. CrewAI handles the connection and makes the searchgametimes tool available automatically.

Q: How is my search history protected when using CrewAI?

Each searchgametimes call is an independent, stateless transaction. The server processes the request for game completion data and returns the result without linking it to a specific user profile or storing your search history.

Equip your CrewAI agents with HowLongToBeat data to create autonomous teams for gaming research and content creation.

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 CrewAI

Create your Vinkius account to connect HowLongToBeat to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Role-Based Data Gathering

Assign a 'Game Researcher' agent in your crew the specific job of gathering data. This agent's only tool can be `search_game_times` from this MCP server, keeping it focused and efficient. Another agent, a 'Content Strategist,' can then take the researcher's findings—a list of games and their completion times—and decide which titles are best for a 'Top 10 Shortest RPGs' article. CrewAI lets you build an assembly line for content.

Autonomous Market Analysis

Your CrewAI team can monitor new game releases. One agent spots a new title, passes the name to a second agent who uses `search_game_times` to get its estimated length, and a third agent compares that length to the game's price to calculate a value score. This entire process runs autonomously. You can have your crew generate a daily report of the best value-for-money new releases without any human intervention. It's a powerful way to automate niche market research.

Filter Tools for Your CrewAI Agents

This MCP Server integrates directly into your CrewAI setup. You can grant the `search_game_times` tool to your entire crew, or use `tool_filter` to give it only to a specific agent, like your designated researcher. This lets you enforce specialization. Your writer agent doesn't need to know how to fetch game data, it just needs to receive it from the researcher. This separation of concerns is what makes CrewAI effective for complex tasks.

Setup guide

Set up HowLongToBeat MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke HowLongToBeat tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="HowLongToBeat Analyst",
    goal="Access and analyze HowLongToBeat data via MCP.",
    backstory="Expert analyst with direct HowLongToBeat access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent HowLongToBeat transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="HowLongToBeat Analyst",
        goal="Access and analyze HowLongToBeat data via MCP.",
        backstory="Expert analyst with direct HowLongToBeat access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent HowLongToBeat transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

A 'Researcher' agent can use `search_game_times` to gather data on 10 games. A 'Writer' agent then takes this data from the crew's shared memory and drafts an article, like '10 Great Games You Can Beat in a Weekend.'

Just pass the Vinkius MCP server URL into the `mcps` list when you define your Agent in Python. CrewAI handles the connection and makes the `search_game_times` tool available automatically.

Yes, that's a perfect use case. Set up a sequential crew. The first agent finds a list of 'award-winning indie games,' and the second agent iterates through that list, calling `search_game_times` for each title.

It works for both. In a sequential crew, one agent can gather the data for the next. In a hierarchical crew, a manager agent could delegate the task of finding game times to a subordinate specialist agent.

Each `search_game_times` call is an independent, stateless transaction. The server processes the request for game completion data and returns the result without linking it to a specific user profile or storing your search history.

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