How to Use the Cal.com MCP in LlamaIndex

Q: How can I connect the Cal.com MCP server to LlamaIndex?

Install the llama-index-tools-mcp package and create a BasicMCPClient with your Vinkius endpoint. Then, wrap it in an McpToolSpec to generate a list of tools for your LlamaIndex agent.

Q: Can I filter which Cal.com tools my LlamaIndex agent can use?

Yes, the McpToolSpec supports an allowedtools filter. You can provide a list of tool names, like 'listbookings', 'getbooking', to restrict the agent to read-only operations if needed.

Turn your Cal.com activity into a searchable knowledge base with LlamaIndex. Ask questions about past meetings and booking patterns.

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 LlamaIndex

Create your Vinkius account to connect Cal.com to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Your Meeting History

Connect LlamaIndex to your Cal.com account to build a living history of your schedule. The agent can periodically run `list_bookings` and index the results. This creates a vector store of your past and future meetings, complete with attendees, titles, and times. Once indexed, you can ask natural language questions about your scheduling data. For instance: "Who did I meet with most last quarter?" or "What was the subject of my last meeting with the design team?" Your agent finds the answer from your actual booking data, not a guess.

Ground Your Agent in Reality

This MCP server gives your LlamaIndex agent a direct line to your real-world schedule. Your agent's responses are grounded in the data fetched from tools like `get_booking` and `get_current_user`. The result is a system that can answer questions with facts from your calendar. This approach combines live data access with a searchable index. You can build a RAG application that pulls your current availability from `get_schedules` while also searching your indexed history to see when you last met with someone. It's a powerful way to add context to scheduling decisions.

Query Your Scheduling Configuration

Don't just index bookings; index your setup. Have your agent run `list_event_types` and `get_schedules` to create a knowledge base of how your Cal.com account is configured. This lets you ask questions like, "Which of my event types are 30 minutes long?" or "Show me all events that use my 'Weekend' schedule." This is great for auditing or just remembering how you set things up. Instead of clicking through the Cal.com interface, you just ask your agent. It queries the indexed data and gives you an immediate, accurate answer.

Setup guide

Set up Cal.com MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Cal.com MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Cal.com tools.",
)
response = await agent.run("List recent Cal.com data")

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 LlamaIndex

Install the `llama-index-tools-mcp` package and create a `BasicMCPClient` with your Vinkius endpoint. Then, wrap it in an `McpToolSpec` to generate a list of tools for your LlamaIndex agent.

Yes. While LlamaIndex is strong at querying, it can also execute actions. The agent has access to the `create_booking` tool, so you can ask it to schedule a new meeting based on your query results or other context.

First, you need to build an index of your bookings by having the agent run `list_bookings`. After that, you can ask your agent questions in plain English. It will perform a semantic search over the indexed data to find the answer.

Yes, the `McpToolSpec` supports an `allowed_tools` filter. You can provide a list of tool names, like `['list_bookings', 'get_booking']`, to restrict the agent to read-only operations if needed.

The server only touches your Cal.com booking data, user profile information, and event type settings when a tool is called. Your Vinkius endpoint token handles authentication, and the MCP server itself runs in an ephemeral, zero-trust environment. It has no access beyond the specific Cal.com permissions you've granted.

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