How to Use the GiantBomb MCP in Google ADK

Q: How do I connect the GiantBomb tools to a Google ADK agent?

Use the McpToolset class with your Vinkius HTTP URL to load the server. Pass this toolset into your LlmAgent constructor, which instantly exposes the database search capabilities.

Q: Can a Google ADK agent combine GiantBomb data with BigQuery?

Yes, you can write an agent that queries GiantBomb via getgame and joins that metadata with your BigQuery tables. The ADK handles the data flow between both sources natively.

Q: Can I limit my agent to only search for video game platforms?

You can configure your toolset to only expose getplatform and listplatforms. This prevents the agent from calling other endpoints, keeping its focus entirely on hardware.

Give your Google ADK agents direct access to the GiantBomb database using this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect GiantBomb MCP to Google ADK

Create your Vinkius account to connect GiantBomb to Google ADK 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 GiantBomb with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze GiantBomb databases with Gemini long-context

Connect Gemini's massive context window to GiantBomb's extensive gaming registry. Your agent can pull hundreds of game records using `list_games` and analyze decades of industry trends in a single turn. Using this MCP Server allows your Google ADK agent to cross-reference game details with your BigQuery datasets. You can map public gaming trends directly against internal sales projections without manual data exports.

Filter GiantBomb tools for enterprise Google ADK agents

Control exactly what resources your enterprise agents can access. Use the `tool_names` filter in the ADK to expose only specific tools like `get_platform` or `list_companies` to your agent. This restriction keeps your model focused on relevant tasks. It prevents Gemini from wasting tokens on irrelevant tools when it only needs to look up hardware specifications.

Execute secure search operations on Google Cloud

Run your gaming search workflows inside a secure Google Cloud ecosystem. The ADK connects to this MCP Server over secure HTTP, letting your agent run `search` safely. You get clean, structured JSON payloads directly from GiantBomb. The agent parses company founders via `get_company` and character details through `get_character` without raw HTML scraping.

Setup guide

Set up GiantBomb MCP in Google ADK

Prerequisites

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

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with GiantBomb tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="GiantBomb_agent",
    model="gemini-2.0-flash",
    instruction="You have access to GiantBomb tools via MCP.",
    tools=mcp_tools,
)

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 GiantBomb. 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 GiantBomb 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 GiantBomb MCP in Google ADK

Use the `McpToolset` class with your Vinkius HTTP URL to load the server. Pass this toolset into your `LlmAgent` constructor, which instantly exposes the database search capabilities.

Yes, you can write an agent that queries GiantBomb via `get_game` and joins that metadata with your BigQuery tables. The ADK handles the data flow between both sources natively.

Yes, the server feeds structured game data directly into Gemini's context. You can retrieve long lists of characters with `list_characters` and let the model analyze the entire dataset at once.

You can configure your toolset to only expose `get_platform` and `list_platforms`. This prevents the agent from calling other endpoints, keeping its focus entirely on hardware.

Your GiantBomb API key is encrypted at rest and injected only during runtime inside an isolated, zero-trust sandbox. Your gaming search strings are never logged or cached on our servers.

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