How to Use the Cat Facts MCP in Google ADK

Q: How do I connect the Cat Facts server to my Google ADK agent?

You'll use the McpToolset class. Instantiate it with the Vinkius server URL and pass the toolset into the tools list when creating your LlmAgent. That's it.

Q: Can I hide certain Cat Facts tools from my Google ADK agent?

Yes. When you set up the McpToolset, you can pass a toolnames list to explicitly define which tools are visible. For instance, you could allow getrandomcatfact but block listcatbreeds.

Connect Gemini to cat facts. The Google ADK makes this MCP server a native tool for your enterprise agents on Google Cloud.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cat Facts MCP to Google ADK

Create your Vinkius account to connect Cat Facts 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 Cat Facts with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze Breed Data in BigQuery

Pull a complete list of cat breeds using the `list_cat_breeds` tool. Your Gemini agent gets this data and can immediately cross-reference it with your own datasets stored in BigQuery. It's not just about getting a list; it's about putting it to work. Imagine asking your agent to find which cat breeds you're missing from a customer interest table. It can fetch the master list from this MCP server, query your database, and give you the answer in one go. That's what a native Google Cloud integration does.

Long-Context Cat Fact Chains

Take advantage of Gemini's massive context window. Your agent can call `get_random_cat_fact` or `list_cat_facts` multiple times, holding dozens of facts in its memory without losing track of the conversation. This means you can ask for more complex summaries or analyses. For example, 'Get 20 cat facts and tell me which ones are about diet.' An agent with a smaller context would fail, but Gemini handles it easily.

Google ADK Toolset Integration

Adding Cat Facts to your agent is straightforward with the `McpToolset`. You point it at the server URL, and it becomes another tool in your agent's belt, right alongside your existing Google Cloud services like Vertex AI or Cloud Storage. This setup lets you build powerful workflows. Your agent can use `list_cat_facts` to get information, then pass that info to a Vertex AI endpoint for further processing, all within the same session. You can also use the `tool_names` filter to expose only the specific tools you want the agent to see.

Setup guide

Set up Cat Facts 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 Cat Facts 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="Cat Facts_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Cat Facts 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 Cat Facts. 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 Cat Facts 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 Cat Facts MCP in Google ADK

You'll use the `McpToolset` class. Instantiate it with the Vinkius server URL and pass the toolset into the `tools` list when creating your `LlmAgent`. That's it.

Yes. When you set up the `McpToolset`, you can pass a `tool_names` list to explicitly define which tools are visible. For instance, you could allow `get_random_cat_fact` but block `list_cat_breeds`.

Absolutely. That's a primary use case. Your agent can fetch data from the Cat Facts server and then use its native BigQuery tool to run queries that combine both datasets.

It lets your agent perform more complex tasks. It can gather a large number of facts with `list_cat_facts` and then reason over the entire set to find patterns or create detailed summaries, which isn't possible with a small context window.

It only sees the direct requests for cat facts or breed names. Your Google Cloud project data, credentials, and BigQuery tables are never exposed. Vinkius isolates every single call in a zero-trust sandbox that has no access to your environment.

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