How to Use the HighLevel MCP in AutoGen

Q: Can I use AutoGen to automate HighLevel task lists?

Yes. One agent can call listcontacttasks to identify open items, while another agent decides how to resolve them based on your custom prompt instructions.

Q: How do AutoGen agents handle HighLevel booking conflicts?

The agents debate the availability returned by getcalendarfreeslots. If a slot is taken during the debate, the validator agent rejects the plan and requests fresh slots.

Coordinate multi-agent debates in AutoGen to manage your HighLevel contacts and calendars without collisions.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect HighLevel MCP to AutoGen

Create your Vinkius account to connect HighLevel 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 HighLevel with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Resolve HighLevel contact duplicates in AutoGen

`search_contacts` is the tool your AutoGen search agent uses to verify if a lead already exists in your CRM via this MCP Server. The search agent passes the results to a validator agent to check for matching emails or phone numbers. If no match is found, the validator agent instructs the writer agent to call `create_contact`. This multi-agent debate prevents your CRM from getting cluttered with duplicate profiles.

Deconflict HighLevel calendars with AutoGen

`get_calendar_free_slots` provides the raw availability data that your AutoGen scheduling agent analyzes. A separate quality-assurance agent reviews the selected slot against timezone rules before booking. Once both agents agree on the slot, the booking agent executes `create_appointment`. This consensus-driven approach eliminates double-bookings and scheduling conflicts.

Manage HighLevel pipeline opportunities in AutoGen

`search_opportunities` allows your AutoGen sales agent to locate active deals within specific pipelines. The agent shares this opportunity data with an account manager agent to coordinate next steps. The account manager agent then calls `create_contact_task` to assign follow-up actions to the team. This distributes CRM management across specialized agents working in sync.

Setup guide

Set up HighLevel 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 HighLevel 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="HighLevel_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

You register the HighLevel MCP Server tools with your assistant agents. A group chat manager then directs which agent calls `search_contacts` and which one updates the pipeline based on the conversation flow.

Yes. One agent can call `list_contact_tasks` to identify open items, while another agent decides how to resolve them based on your custom prompt instructions.

Yes, the server tools map directly to AutoGen's schema requirements. The adapter handles the conversion of tools like `create_appointment` out of the box.

The agents debate the availability returned by `get_calendar_free_slots`. If a slot is taken during the debate, the validator agent rejects the plan and requests fresh slots.

All traffic passing through this MCP Server to the HighLevel endpoints is encrypted using TLS 1.3. Vinkius never caches your contact records or calendar details, keeping your client database private.

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