How to Use the Calendly MCP in AutoGen

Q: How would an AutoGen agent cancel a meeting in Calendly?

An agent would be given the cancelevent tool. You could design a system where one agent identifies the event to cancel, and a UserProxyAgent asks you for confirmation before the tool is actually executed.

Q: Can I use AutoGen to find out who is in my Calendly organization?

Definitely. The listorgmembers tool is designed for this. An "HR Agent" could use this tool to get a list of all team members and their roles within your AutoGen conversation.

Q: How do I get a list of all possible meeting types?

The listeventtypes tool provides this. An agent can call it to see all the meeting templates you've created in Calendly, like "15-min Quick Sync" or "60-min Project Demo."

Build teams of AI agents that debate and manage Calendly scheduling for you with AutoGen.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Calendly MCP to AutoGen

Create your Vinkius account to connect Calendly 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 Calendly with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Let AI Agents Negotiate Schedules

AutoGen is about conversations between agents. You can create a "Scheduling Agent" that uses `get_available_times` to propose meeting slots. Then, a "Logistics Agent" could use `get_event_type` to check if the proposed meeting's duration and settings are appropriate for the attendees. The agents debate the options. One agent might find a time, but another could flag that it's outside someone's normal hours by checking their schedule via `list_availability`. They work together, using different Calendly tools to converge on the best possible meeting time.

The AutoGen MCP Server Workflow

Build a whole team of specialized agents. An "Admin Agent" could be responsible for housekeeping tasks, like using `list_scheduled_events` to find old meetings and `cancel_event` to clean them up. A "Recruiting Agent" could be focused on using `list_event_types` to find the right interview loop for a candidate. These agents don't just act; they report to a manager agent or to you. The Admin Agent could propose a list of events to cancel, and you (or another agent) would give the final approval. This MCP Server provides the specific tools each agent needs to play its part in the conversation.

Coordinate Your Team with AI Agents

Managing a team's calendar is a perfect task for AutoGen. One agent can use `list_org_members` to get the team roster. Another agent can then check who is attending a specific meeting with `list_invitees` and cross-reference it with the master list. This enables complex, collaborative workflows. For instance, if a key person is missing from an invitee list, an "Alert Agent" could flag it. Another agent could then try to find a better time for the whole group. It's about using multiple agents to check each other's work and make smarter decisions.

Setup guide

Set up Calendly 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 Calendly 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="Calendly_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Calendly 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="Calendly_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Calendly 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 Calendly. 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 Calendly 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 Calendly MCP in AutoGen

Yes, that's exactly what AutoGen is for. The first agent would use `get_available_times`. The second could review the proposal and then either confirm or reject it, creating a collaborative workflow.

An agent would be given the `cancel_event` tool. You could design a system where one agent identifies the event to cancel, and a UserProxyAgent asks you for confirmation before the tool is actually executed.

Definitely. The `list_org_members` tool is designed for this. An "HR Agent" could use this tool to get a list of all team members and their roles within your AutoGen conversation.

The `list_event_types` tool provides this. An agent can call it to see all the meeting templates you've created in Calendly, like "15-min Quick Sync" or "60-min Project Demo."

Your Calendly data, such as organization member lists or event details, is never persisted by the MCP server. Each tool call is handled in a dedicated, zero-trust sandbox that is destroyed after your request completes. Your API token is the only key.

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