How to Use the Bored MCP in Google ADK

Q: How do I add the Bored MCP Server to my Google ADK agent?

Instantiate the McpToolset with your Vinkius HTTP server parameters. Pass that toolset into the tools list of your LlmAgent to let Gemini call the activity tools.

Q: Can I combine Bored search results with BigQuery data in Google ADK?

Absolutely, you can have your agent fetch a task using findactivity and then run a BigQuery SQL query to see if the user has done similar things before. The long-context window of Gemini makes handling both data sources simple.

Q: How do I limit my agent to only use the random tool?

Use the optional toolnames filter when initializing your toolset. Pass only getrandomactivity in the list to hide the search and key-based tools from the model.

Equip your Google ADK enterprise agents with Bored tools to match user downtime with curated activities.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Bored MCP to Google ADK

Create your Vinkius account to connect Bored 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 Bored with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query Bored parameters inside Google ADK workflows

The `find_activity` tool connects your Google ADK agent to a database of curated tasks filtered by cost and participant count. Because Gemini models handle massive context windows, your agent can cross-reference these activities with historical user data stored in BigQuery. Feeding these search results directly into your enterprise pipeline allows for deeply personalized recommendations. Your agent processes the entire list of suggestions in a single reasoning step.

Use specific keys to pull Bored data with Google ADK

The `get_activity_by_key` tool fetches exact activity profiles to keep your database lookups consistent. When building with this MCP Server, you can pass the toolset directly to your `LlmAgent` using streamable HTTP parameters. If you want to restrict access, use the `tool_names` filter in the ADK to only expose this specific key lookup tool. This keeps your agent focused and prevents it from executing unwanted random queries.

Inject random Bored activities into long-context chats

The `get_random_activity` tool provides a quick way to break a loop when your user needs a spontaneous suggestion. The MCP Server integrates directly via the `McpToolset` class to feed ideas straight to your agent. Gemini parses the random output and compares it against complex user profiles in Vertex AI. This means you do not have to write manual API wrappers; the model simply calls the tool when the conversation stalls.

Setup guide

Set up Bored 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 Bored 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="Bored_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Bored 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 Bored API. 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 Bored 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 Bored MCP in Google ADK

Instantiate the `McpToolset` with your Vinkius HTTP server parameters. Pass that toolset into the `tools` list of your `LlmAgent` to let Gemini call the activity tools.

Absolutely, you can have your agent fetch a task using `find_activity` and then run a BigQuery SQL query to see if the user has done similar things before. The long-context window of Gemini makes handling both data sources simple.

Yes, this server is hosted on Vinkius and uses the streamable HTTP transport. This fits perfectly with the ADK's `StreamableHttpServerParameters` configuration.

Use the optional `tool_names` filter when initializing your toolset. Pass only `get_random_activity` in the list to hide the search and key-based tools from the model.

Yes, only the specific parameters like participant count or price limits are sent to the Bored server. Your proprietary enterprise data in Vertex AI or BigQuery remains isolated within your Google Cloud boundary.

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