How to Use the Cal.com MCP in AutoGen

Q: How do AutoGen agents negotiate Cal.com bookings?

One agent uses getslots to find open times, while another checks internal databases. They trade suggestions in a chat loop until they agree on a time, then execute createbooking.

Q: Can I limit which Cal.com tools an AutoGen agent can use?

Yes, you can register only specific tools like listbookings with your assistant agent. This prevents conversational agents from accidentally canceling meetings or changing team settings.

Q: Does AutoGen support the Cal.com credit system?

It does, by using the getcredits and chargecredits tools. You can build a specialized billing agent that manages client balances before any scheduling occurs.

Let your AutoGen agents debate schedule conflicts and book meetings on Cal.com automatically using this multi-agent MCP Server.

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 AutoGen

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Resolve calendar conflicts via agent debate

Hooking up this Cal.com MCP Server exposes `get_busy_times` to let your AutoGen agents negotiate open slots before making a decision. One AutoGen agent might propose a time, while a second agent checks the Cal.com busy list to flag internal conflicts. The AutoGen agents debate until they find a Cal.com slot that works for everyone. Once they reach consensus, the coordinator AutoGen agent triggers `create_booking` to finalize the appointment on the Cal.com calendar.

Manage Cal.com credits in AutoGen

Calling the `get_credits` tool allows your AutoGen billing agent to check user balances before a scheduling agent is allowed to book a paid Cal.com meeting. If the Cal.com credit balance is too low, the AutoGen billing agent halts the conversation and requests a top-up. Once confirmed, the AutoGen agents call `charge_credits` to deduct the appropriate amount from the Cal.com account. This automated AutoGen escrow workflow prevents unpaid consultations from ever reaching your hosts' Cal.com calendars.

Automated webhook setup for team alerts

Deploying the `create_webhook` tool lets your AutoGen developer agent register new event listeners on Cal.com dynamically during runtime. When a Cal.com booking event triggers, the agent sets up the webhook to notify the rest of the AutoGen multi-agent swarm. This keeps your entire Cal.com integration in sync across AutoGen without manual configuration. The AutoGen agents monitor these Cal.com webhooks to update internal lead records and prepare meeting briefs automatically.

Setup guide

Set up Cal.com MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Cal.com tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Cal.com_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Cal.com data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Cal.com_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Cal.com data")
    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 AutoGen

One agent uses `get_slots` to find open times, while another checks internal databases. They trade suggestions in a chat loop until they agree on a time, then execute `create_booking`.

Yes, you can register only specific tools like `list_bookings` with your assistant agent. This prevents conversational agents from accidentally canceling meetings or changing team settings.

It does, by using the `get_credits` and `charge_credits` tools. You can build a specialized billing agent that manages client balances before any scheduling occurs.

You import the MCP extension, connect to your Vinkius HTTP endpoint, and pass the adapted tools list directly to your AssistantAgent constructor. The schema conversion is handled automatically.

No. Your scheduled bookings, organizer profiles, and busy times are transmitted through Vinkius's zero-trust sandboxes via our secure MCP gateway. The raw data remains encrypted and ephemeral, never stored on our host servers.

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