How to Use the Betterfly MCP in LangChain

Q: How do I connect the Betterfly MCP Server to LangChain?

Install langchain-mcp-adapters and langgraph. Use MultiServerMCPClient pointing to your Vinkius endpoint, then pass the tools to createagent.

Q: Can LangChain trigger Betterfly team challenges automatically?

Yes. Your agent can evaluate data from getcompanymetrics and decide to execute createchallenge. You define the threshold in your prompt.

Q: How do I check user insurance coverage?

Have your agent run listinsurance. It returns the covered scopes for your corporate plan directly into your workflow.

Build multi-step HR and ESG reasoning pipelines by connecting LangChain agents to Betterfly.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Betterfly MCP to LangChain

Create your Vinkius account to connect Betterfly 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 Betterfly with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query Betterfly metrics inside your LangChain pipeline.

Your agent needs to pull corporate wellness stats before deciding on a new initiative. You drop the Betterfly MCP Server into your LangChain setup. Now, your ReAct agent can call `get_company_metrics` to grab global step counts and active participation rates. The output feeds directly into the next step of your chain. If the numbers look low, the agent automatically triggers `create_challenge` to kick off a new team activity. You track the exact token usage and latency for these calls right in LangSmith.

Automate ESG reporting across multiple systems.

Pulling sustainability data usually means exporting spreadsheets. With this setup, your agent runs `get_impact_stats` to grab the latest social metrics and `list_donations` to see corporate giving. It formats that raw JSON into a readable summary. Because you are working within a chain, you can send that summary straight to a vector store or another API. The agent does the heavy lifting, pulling facts from the MCP Server instead of guessing.

Manage employee wellness rewards programmatically.

HR teams spend hours manually tracking who earned what. You can build an agent that checks `list_activities` to see who hit their fitness goals this month. Once it confirms the target, the agent fires off `assign_reward` to issue the bonus. It can even check `get_user_rewards` to make sure it doesn't double-pay someone. You build the logic once, and the agent handles the execution based on the rules you set.

Setup guide

Set up Betterfly 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 Betterfly 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({
    "betterfly-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 Betterfly 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 Betterfly. 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 Betterfly 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 Betterfly MCP in LangChain

Install `langchain-mcp-adapters` and `langgraph`. Use `MultiServerMCPClient` pointing to your Vinkius endpoint, then pass the tools to `create_agent`.

Yes. Your agent can evaluate data from `get_company_metrics` and decide to execute `create_challenge`. You define the threshold in your prompt.

LangChain lets you build multi-step reasoning. The agent reads `get_impact_stats`, decides what the data means, and passes it to your next tool automatically.

Have your agent run `list_insurance`. It returns the covered scopes for your corporate plan directly into your workflow.

Vinkius runs this integration in a V8 Isolate Sandbox. When your LangChain agent pulls user step counts via `list_activities`, that data stays ephemeral and is never stored on our infrastructure.

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