How to Use the Cal.com MCP in LangChain

Q: How do I start using the Cal.com MCP server with LangChain?

First, install the adapter with pip. Then, instantiate the MultiServerMCPClient with your Vinkius endpoint URL and pass the server's tools to your agent constructor. Your agent can then invoke Cal.com tools like createbooking as part of a chain.

Q: Can my LangChain agent automatically cancel Cal.com bookings?

Yes. The cancelbooking tool lets your agent cancel any existing appointment by its ID. Be careful, as this action cannot be undone. You could build a chain that first lists bookings and asks for confirmation before canceling.

Q: What's the best way to find my available slots in Cal.com using LangChain?

Your agent should first use listeventtypes to identify the correct meeting type for the booking. Then, use geteventtype to find its associated schedule ID. With that, your agent can determine availability based on the schedule's rules.

Q: Can I use this MCP server to manage multiple Cal.com accounts?

Yes, by creating separate client instances. Each MultiServerMCPClient instance in your code can be configured with a different Vinkius endpoint token, connecting it to a different Cal.com account.

Build autonomous agents that chain Cal.com actions with LangChain. Find open slots, book meetings, and manage your schedule step-by-step.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cal.com MCP to LangChain

Create your Vinkius account to connect Cal.com 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 Cal.com with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Scheduling Operations

Create agents that reason through multi-step scheduling tasks. An agent can use `get_current_user` to get your timezone, then `list_event_types` to find the right meeting type, and finally call `create_booking` to schedule it. It's a sequence of decisions, not just one action. Each tool call is a link in a chain, with the output of one feeding the next. This lets you build complex logic, like finding all upcoming meetings with `list_bookings` and then automatically canceling any that don't match specific criteria using `cancel_booking`. LangSmith gives you a full trace of every step.

A Cal.com MCP Server for LangChain

This isn't just about calling a single function. You give your agent a toolbox of Cal.com operations and a goal. The agent then figures out the right sequence of tools to achieve it. It can handle dynamic situations, like checking for conflicts before creating a new event. Your agent decides which tools to call and in what order based on the results it gets along the way. This MCP Server gives your LangChain agent direct access to list, create, and cancel bookings, manage event types, and query your own availability schedules.

Audit and Manage Event Types

Your agent can inventory your entire meeting setup. Use `list_event_types` to pull all your meeting templates, then loop through them with `get_event_type` to check their specific configurations. It's a great way to audit for consistency or find which events use outdated schedules. You can also build chains that manage availability. For example, an agent could check your primary calendar for a last-minute conflict, find the corresponding schedule with `get_schedules`, and then temporarily disable an event type for you. It's active calendar management, done by your agent.

Setup guide

Set up Cal.com 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 Cal.com 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({
    "calcom-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 Cal.com 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 Cal.com. 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 Cal.com 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 Cal.com MCP in LangChain

First, install the adapter with pip. Then, instantiate the `MultiServerMCPClient` with your Vinkius endpoint URL and pass the server's tools to your agent constructor. Your agent can then invoke Cal.com tools like `create_booking` as part of a chain.

Yes. The `cancel_booking` tool lets your agent cancel any existing appointment by its ID. Be careful, as this action cannot be undone. You could build a chain that first lists bookings and asks for confirmation before canceling.

Your agent should first use `list_event_types` to identify the correct meeting type for the booking. Then, use `get_event_type` to find its associated schedule ID. With that, your agent can determine availability based on the schedule's rules.

Yes, by creating separate client instances. Each `MultiServerMCPClient` instance in your code can be configured with a different Vinkius endpoint token, connecting it to a different Cal.com account.

The server only accesses the data needed for the tools you call. This includes your user profile info, booking details, event type configurations, and schedule availability. Vinkius sandboxes the MCP server, and it only has the permissions granted by the API key you configured for Cal.com.

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