How to Use the Bored MCP in LangChain

Q: Can I trace Bored tool execution inside LangChain using LangSmith?

Yes, LangSmith captures every call to findactivity or getrandomactivity automatically. You see the exact latency, token count, and activity parameters passed to the server.

Get boredom-busting activities into your LangChain chains and trace every decision with LangSmith.

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 LangChain

Create your Vinkius account to connect Bored to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Inject Bored MCP Server into LangChain Pipelines

The `find_activity` tool feeds curated ideas directly into your LangChain runnables. We pass the price and accessibility parameters from one step of your chain straight into the next node without manual parsing. Your agent inspects the output of the Bored MCP Server to decide if a recreation suggestion fits the user's budget. LangSmith traces the exact inputs and outputs of this decision loop in real time.

Targeted Activity Retrieval by Key

The `get_activity_by_key` tool fetches specific, pre-determined tasks when your pipeline needs an exact match. You can hardcode key activities into your LangChain prompt templates to trigger precise responses. LangChain's native adapters handle the state of these calls across your conversational memory. This ensures the agent remembers the exact activity key throughout a multi-turn dialogue.

Randomized Icebreakers for Multi-Agent Runs

The `get_random_activity` tool injects unpredictable team-building ideas into your LangChain execution chains. Your agent pulls a random task to break the ice before starting heavy processing tasks. You configure this tool as a fallback node in your LangGraph setup. When other APIs fail, the chain defaults to a lighthearted activity to keep the user engaged.

Setup guide

Set up Bored MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Bored tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "bored-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Bored transactions"
    })
    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 LangChain

Yes, LangSmith captures every call to `find_activity` or `get_random_activity` automatically. You see the exact latency, token count, and activity parameters passed to the server.

The adapter wraps our server tools in standard LangChain tool structures, raising a clean exception if `get_activity_by_key` fails. Your agent can catch this error and retry with different criteria.

Yes, by wrapping our connection in a LangChain session. This allows your agent to reference previously suggested activities in subsequent conversation turns.

Run the pip installation for our adapter package, then point your configuration to our hosted URL. You will have live activity data flowing into your terminal in under two minutes.

We isolate your activity search parameters, budget filters, and participant counts in a secure, ephemeral V8 sandbox. None of your boredom queries or activity keys are stored on our servers after the session closes.

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