How to Use the GoHighLevel MCP in Pydantic AI

Q: How do I register the GoHighLevel MCP Server in Pydantic AI?

You instantiate MCPToolset with your Vinkius HTTP endpoint and pass it to the toolsets argument of your Agent. Avoid using the deprecated MCPServerHTTP class; the unified toolset class is the modern, supported approach.

Build type-safe integrations with the GoHighLevel MCP Server using Pydantic AI to stop bad API data.

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 Pydantic AI

Create your Vinkius account to connect GoHighLevel to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Runtime schema validation with this MCP Server

Stop worrying about silent failures when calling the GoHighLevel MCP Server. When your agent calls `get_contact` or `list_pipelines`, Pydantic AI validates the returned JSON payload against strict Python type models at runtime. If the GoHighLevel API structure changes unexpectedly, your system raises an explicit validation error immediately. This strict typing keeps your production database clean. Your agent cannot proceed with malformed data, preventing corrupted records from creeping into your sales pipeline. It's the safest way to run LLM-driven CRM operations.

Model-agnostic execution for reliable CRM workflows

Swap your underlying LLM without rewriting your GoHighLevel MCP Server integration code. Whether you run your agent on OpenAI, Anthropic, or a local open-source model, the tool schemas for `create_contact` and `list_opportunities` remain perfectly consistent. Pydantic AI handles the translation layer perfectly. This flexibility lets you optimize for cost or speed depending on the task. Use a smaller, faster model to run `list_conversations` and inspect messages, but switch to a smarter model when generating personalized outreach text.

Structured campaigns and form discovery

Extract clean, typed lists of your marketing assets using the GoHighLevel MCP Server. By calling `list_campaigns` and `list_forms`, your agent gets structured data objects that fit perfectly into your application's internal data models. You can easily map these assets to front-end UI components or internal routing tables. This makes building custom admin dashboards or internal tools incredibly fast. Your Python code can safely assume the structure of every form and email sequence, reducing the amount of defensive boilerplate code you have to write.

Setup guide

Set up GoHighLevel MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "gohighlevel-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to GoHighLevel tools.",
)

result = await agent.run("List recent GoHighLevel transactions")
print(result.output)

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 Pydantic AI

You instantiate `MCPToolset` with your Vinkius HTTP endpoint and pass it to the `toolsets` argument of your `Agent`. Avoid using the deprecated `MCPServerHTTP` class; the unified toolset class is the modern, supported approach.

The framework will raise a validation error instantly. This prevents your agent from processing corrupt data from `list_contacts` or `list_opportunities` and guarantees that only fully validated payloads reach your application logic.

Yes. Because the framework is model-agnostic, you can connect your local LLM to the MCP server. The model will still be forced to adhere to the strict schemas defined for tools like `send_message` and `create_contact`.

No. Vinkius hosts and manages the server execution environment for you. Your Python application simply connects to the secure, hosted HTTP endpoint, meaning you don't have to manage Node or Docker processes locally.

All CRM payloads—including sensitive customer messages and contact profiles—are processed inside ephemeral V8 isolates. No data is stored, logged, or cached on Vinkius. We use strict network isolation to ensure your CRM data moves securely between GoHighLevel and your application.

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