How to Use the Bored MCP in AutoGen

Q: How do AutoGen agents share access to the Bored server tools?

You register our tools using the mcpservertools helper and pass the resulting list to your AssistantAgent. All agents in your AutoGen group chat can then invoke these tools during their conversation.

Let your AutoGen agents debate the perfect Bored activity and reach a consensus based on real-time filters.

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 AutoGen

Create your Vinkius account to connect Bored to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Deploy Bored MCP Server Tools in AutoGen Debates

The `find_activity` tool gives your AutoGen agents a structured list of options to discuss and filter. One agent can request low-cost options while another filters for accessibility. They negotiate the best choice using the raw JSON payload returned by our server. This collaborative process ensures the final suggestion meets every constraint before presenting it to the user.

Targeted Resolution with Specific Activity Keys

The `get_activity_by_key` tool allows a coordinator agent to retrieve a specific record during a multi-agent workflow. When one agent proposes a key, another checks its validity. AutoGen's conversational patterns let agents verify activity details back and forth. If the key points to an expensive task, a budget-focused agent can veto the decision.

Injecting Spontaneity into Agent Conversations

The `get_random_activity` tool provides unexpected prompts to break deadlocks in AutoGen conversations. When agents cannot agree on a course of action, a random seed restarts the debate. This injects a dynamic element into your simulated agent environments. AutoGen's conversational agents react to the random task, creating highly varied and lifelike interactions.

Setup guide

Set up Bored MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Bored tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

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

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Bored_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Bored data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

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

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Bored_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Bored data")
    print(result.messages[-1].content)

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 AutoGen

You register our tools using the `mcp_server_tools` helper and pass the resulting list to your `AssistantAgent`. All agents in your AutoGen group chat can then invoke these tools during their conversation.

Yes, you can program a critic agent to analyze the output of `find_activity`. If the proposed activity doesn't match the user's accessibility needs, the critic agent demands a new search.

Our server uses the standard MCP schema, which the AutoGen MCP tool adapter converts automatically. Your agents get clean, typed schemas for all activity parameters without manual mapping.

We support both stdio and Streamable HTTP transports. You can configure the connection using simple URL parameters in your agent startup script.

Yes. All activity keys, participant counts, and pricing queries are processed in an ephemeral, isolated V8 sandbox. This secure MCP environment ensures your team's conversational context and recreation preferences never leave our secure gateway.

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