How to Use the MyTime MCP in LangChain

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

Install langchain-mcp-adapters. Initialize a MultiServerMCPClient with your MyTime endpoint and pass the resulting tools array to createagent.

Q: Can LangChain chain MyTime appointments with my database?

Yes. You build a chain where the agent calls getappointment, formats the JSON response, and pushes it to your Postgres instance using standard LangChain tools.

Q: Does LangSmith trace MyTime tool calls?

It traces every request. You see the exact inputs sent to getavailability and the raw JSON returned, plus execution latency.

Q: How does LangChain handle pagination for MyTime tools?

Your ReAct agent handles it dynamically. If listcustomers returns a next-page token, the agent loops the call until it gathers the complete dataset.

Build multi-step reasoning pipelines that manage your MyTime appointments and staff schedules directly in LangChain.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MyTime MCP to LangChain

Create your Vinkius account to connect MyTime 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 MyTime with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain MyTime MCP Server Tools into Workflows

`list_appointments` feeds directly into your LangChain ReAct agent's decision loop. You build a pipeline that pulls today's schedule, checks the customer history via `list_customers`, and outputs a personalized briefing for the front desk. The output of one MCP tool call becomes the exact input for the next. Your agent decides which action to take based on intermediate API results. If a client cancels, the chain automatically triggers `get_availability` to find the next open slot, then generates a draft email to fill the gap. LangSmith traces every step, showing you exactly how many tokens the operation consumed and where the latency occurred.

Aggregate Staff and Service Data

`list_staff` and `list_services` let your agent read your entire operational catalog in a single pass. You pass the MultiServerMCPClient into your agent setup, giving it read access to the business structure. The agent maps out who works where and what they do. Because LangChain handles state management across multiple turns, your agent remembers the service list while querying `list_locations`. It cross-references which services are available at specific storefronts without needing a hardcoded database. You get dynamic answers based on live MyTime data.

Monitor Business Performance

`list_reviews` and `list_products` give your reasoning pipelines raw data for sentiment and inventory analysis. Your agent pulls the latest 50 reviews and compares them against the products sold that week. It spots trends before a human manager would notice them. You connect this setup to a vector store using LangChain's built-in integrations. The agent reads the raw string from `get_business_info`, structures it, and writes it to your database. You track long-term performance metrics without writing custom API wrappers.

Setup guide

Set up MyTime 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 MyTime 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({
    "mytime-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 MyTime 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 MyTime. 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 MyTime 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 MyTime MCP in LangChain

Install `langchain-mcp-adapters`. Initialize a MultiServerMCPClient with your MyTime endpoint and pass the resulting tools array to `create_agent`.

Yes. You build a chain where the agent calls `get_appointment`, formats the JSON response, and pushes it to your Postgres instance using standard LangChain tools.

It traces every request. You see the exact inputs sent to `get_availability` and the raw JSON returned, plus execution latency.

Your ReAct agent handles it dynamically. If `list_customers` returns a next-page token, the agent loops the call until it gathers the complete dataset.

The server pulls names and phone numbers directly into your agent's active memory. The MCP architecture keeps this transaction ephemeral. Data only persists if you explicitly configure LangChain to write it to disk or a logging service.

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