How to Use the Acuity Scheduling MCP in AutoGen

Q: How can AutoGen agents prevent scheduling conflicts in Acuity Scheduling?

You can assign one agent to find a slot with listavailabletimes and a second agent to act as a verifier. The verifier agent re-runs the check just before the final booking step, ensuring the slot wasn't taken while the agents were 'discussing' it.

Q: How do I get my business info from Acuity into my agent chat?

Use the getaccount tool. An agent can call this to retrieve your business name, address, and other profile settings from Acuity. It's useful for an 'Initializer' agent to confirm it's connected to the right account.

Q: Can I use AutoGen to manage different services in Acuity Scheduling?

Yes. An agent can use listappointmenttypes to get a full list of services you offer. This allows a 'Customer Service' agent to accurately describe options to a user before a 'Scheduler' agent tries to book anything.

Assemble a team of AutoGen agents to debate, plan, and manage your Acuity Scheduling calendar with conversational AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Acuity Scheduling MCP to AutoGen

Create your Vinkius account to connect Acuity Scheduling 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 Acuity Scheduling with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Let agents debate the best appointment time

Design a multi-agent system for smarter scheduling. One agent, the "Scheduler," can use `list_available_times` to propose a few open slots. A second agent, the "Policy Enforcer," can then check those proposals against your business rules, like avoiding back-to-back new client meetings. This conversational approach catches issues a single agent might miss. The agents discuss the options, one pushing for availability and the other for business logic. They arrive at a consensus on the best time to book, all before any action is taken.

Collaborate on business reporting

Have your agents work together to build reports. A "Data-Puller" agent can be tasked with using `list_appointments` to get all the bookings for the last month. It then passes that raw data to an "Analyst" agent. The Analyst agent can then cross-reference appointment types against the `list_calendars` output to see which services are driving the most revenue per provider. It's a powerful way to use AutoGen's conversational structure to get more than just raw data from this MCP Server.

Build a consensus-driven product agent

Create a team of agents to manage your public offerings. One agent can use `list_classes` to monitor enrollment. If a class is almost full, it can propose creating a new one to a "Finance" agent. The Finance agent then uses `list_appointment_types` to check the price and profitability of that class type. They can debate whether it's the right time to add another session. This lets you model complex business decisions with your AutoGen agents and the Acuity MCP tools.

Setup guide

Set up Acuity Scheduling 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 Acuity Scheduling 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="Acuity Scheduling_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

You can assign one agent to find a slot with `list_available_times` and a second agent to act as a verifier. The verifier agent re-runs the check just before the final booking step, ensuring the slot wasn't taken while the agents were 'discussing' it.

Use the `get_account` tool. An agent can call this to retrieve your business name, address, and other profile settings from Acuity. It's useful for an 'Initializer' agent to confirm it's connected to the right account.

Yes. An agent can use `list_appointment_types` to get a full list of services you offer. This allows a 'Customer Service' agent to accurately describe options to a user before a 'Scheduler' agent tries to book anything.

If one of your agents has an appointment ID, it can use the `get_appointment` tool. This is great for a 'Confirmation' agent that needs to verify the details of a booking that another agent made.

Yes. This MCP server processes your Acuity Scheduling appointment and calendar data within the Vinkius zero-trust sandbox. Each tool call is handled as a stateless, isolated transaction, so data from one agent's request is not visible to another outside your AutoGen code.

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