How to Use the Moneypenny MCP in LangChain

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

Install langchain-mcp-adapters and langgraph via pip. Initialize the client using MultiServerMCPClient with the Vinkius transport URL, pull the tools with client.gettools(), and pass them directly to your agent constructor.

Q: Can a LangChain agent query specific date ranges from Moneypenny?

Yes, the agent can use listcallmessages by passing MM/DD/YYYY formatted dates. LangChain's structured parser guarantees the agent formats these parameters correctly before hitting the Vinkius endpoint.

Q: What happens if the Moneypenny API goes offline during a LangChain run?

Your agent can call checkmoneypennystatus at the start of a chain. If the connection fails, LangChain's fallback mechanisms let you route the execution to a backup system or log a clean error.

Link your live receptionist data directly into LangChain multi-step reasoning chains to instantly act on missed phone calls.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Moneypenny MCP to LangChain

Create your Vinkius account to connect Moneypenny 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 Moneypenny with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain live call logs directly into LangChain workflows

Stop letting missed calls sit in a silent inbox. This MCP integration lets your LangChain agents pull active phone messages using `get_today_calls` and immediately feed them into downstream chains. Your agent can evaluate the urgency of a message, match it against your customer database, and draft an immediate response before your competitor even checks their email. By using `list_call_messages` with specific date ranges, you build multi-step pipelines that track recurring client issues. The tool passes clean, formatted data directly into your prompt templates, letting you run sentiment analysis over a week's worth of phone logs without manual data entry.

Trace Moneypenny chat metrics with LangSmith

When your LangChain agent pulls live chat logs using `get_recent_chats` or `get_today_chats`, every single step is monitored. You can trace the exact latency, token count, and tool execution success inside LangSmith to ensure your automated follow-ups stay fast. If an agent fails to parse a chat transcript from `list_chat_logs`, you will see the exact payload that caused the hitch. This visibility helps you refine your prompt chains and ensures your automated system never misinterprets a customer's urgent request.

Multi-tool execution for operational status checks

Your agent can run parallel checks to verify if your communication lines are active. By combining `check_moneypenny_status` with `get_activity_summary` in a single LangGraph run, your system gets a clear picture of today's customer interactions. This lets you build self-healing agentic workflows. If the status check returns an error, the LangChain agent route can automatically notify your engineering team on Slack while queuing up the call logs for processing once the API recovers.

Setup guide

Set up Moneypenny 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 Moneypenny 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({
    "moneypenny-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 Moneypenny 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 Moneypenny. 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 Moneypenny 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 Moneypenny MCP in LangChain

Install `langchain-mcp-adapters` and `langgraph` via pip. Initialize the client using `MultiServerMCPClient` with the Vinkius transport URL, pull the tools with `client.get_tools()`, and pass them directly to your agent constructor.

Yes, the agent can use `list_call_messages` by passing MM/DD/YYYY formatted dates. LangChain's structured parser guarantees the agent formats these parameters correctly before hitting the Vinkius endpoint.

You should manage polling inside your LangGraph state graph to avoid rate limits. Use `get_this_week_chats` or `get_this_month_calls` to pull larger batch datasets instead of hammering the API with constant daily requests.

Your agent can call `check_moneypenny_status` at the start of a chain. If the connection fails, LangChain's fallback mechanisms let you route the execution to a backup system or log a clean error.

Yes, your phone messages and live chat transcripts are protected. Vinkius runs this MCP server in an isolated V8 sandbox, meaning your customer phone numbers and conversation logs are never stored or exposed to external networks.

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