How to Use the GoHighLevel MCP in Google ADK

Q: How do I configure the GoHighLevel MCP Server using the Google ADK?

You initialize McpToolset with your Vinkius HTTP endpoint in your Python environment. Then, pass that toolset directly to your LlmAgent instance, which immediately exposes tools like getcontact and listforms to Gemini.

Q: Can I use Gemini's long context to analyze GoHighLevel campaigns in Google ADK?

Yes. You can pull all active sequences using listcampaigns and feed the entire text structure into Gemini. The model analyzes the copy, compares it with recent conversation logs from listconversations, and suggests optimizations.

Q: How do I restrict Google ADK to specific GoHighLevel tools?

Use the toolnames filter when setting up your McpToolset. If you only want your agent to read data, restrict it to listpipelines and listopportunities, completely blocking write operations like createcontact.

Q: How does the server secure my lead capture forms and calendar bookings?

Every request fetching data from listforms or listcalendars runs through an isolated, zero-trust V8 sandbox. Your customer booking information and form submissions are decrypted only in memory during execution and never persisted on disk.

Connect GoHighLevel to Google ADK to run enterprise CRM agents powered by Gemini's massive context window.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect GoHighLevel MCP to Google ADK

Create your Vinkius account to connect GoHighLevel to Google ADK 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 GoHighLevel with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run deep CRM analysis with the Google ADK

Feed your GoHighLevel MCP Server data directly into Gemini. By connecting this setup to your Google ADK pipelines, you can fetch massive datasets using `list_opportunities` and `list_contacts` without hitting token limits. Gemini's million-token context window digests the whole picture at once. Your agent can cross-reference active deals with historical performance to spot bottlenecks. It doesn't just look at one record; it analyzes the entire sales pipeline to suggest concrete next steps for your sales reps.

Merge BigQuery data with active CRM pipelines

Ground your GoHighLevel MCP Server actions in your enterprise data warehouse. The ADK makes it simple to pull customer lifetime value or usage metrics from BigQuery and use those insights to trigger actions. Your agent can find high-value users and immediately run `create_contact` to get them into your sales loop. This bridges the gap between your analytical data and your operational CRM. You no longer need complex ETL pipelines to sync databases. Your agent queries the warehouse, decides who to target, and updates your CRM in one clean run.

Automated outreach triggered by analytical insights

Let your agent handle CRM outreach using GoHighLevel MCP Server tools. Once your Google ADK agent identifies a target list, it can use `send_message` to dispatch personalized emails or SMS. It can check if a contact is already in a sequence by running `list_campaigns` first to avoid double-messaging. This keeps your outreach highly targeted and timely. Because the agent has access to your full GCP infrastructure, it can time these messages perfectly based on user activity signals, driving higher response rates.

Setup guide

Set up GoHighLevel MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with GoHighLevel tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="GoHighLevel_agent",
    model="gemini-2.0-flash",
    instruction="You have access to GoHighLevel tools via MCP.",
    tools=mcp_tools,
)

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 GoHighLevel. 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 GoHighLevel 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 GoHighLevel MCP in Google ADK

You initialize `McpToolset` with your Vinkius HTTP endpoint in your Python environment. Then, pass that toolset directly to your `LlmAgent` instance, which immediately exposes tools like `get_contact` and `list_forms` to Gemini.

Yes. You can pull all active sequences using `list_campaigns` and feed the entire text structure into Gemini. The model analyzes the copy, compares it with recent conversation logs from `list_conversations`, and suggests optimizations.

Use the `tool_names` filter when setting up your `McpToolset`. If you only want your agent to read data, restrict it to `list_pipelines` and `list_opportunities`, completely blocking write operations like `create_contact`.

Yes. The ADK handles both transport protocols. For production deployments, we recommend using the hosted HTTP transport on Vinkius, which keeps your agent setup stateless and easy to scale.

Every request fetching data from `list_forms` or `list_calendars` runs through an isolated, zero-trust V8 sandbox. Your customer booking information and form submissions are decrypted only in memory during execution and never persisted on disk.

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