How to Use the HighLevel MCP in Pydantic AI

Q: Can Pydantic AI read HighLevel tasks?

Yes. The server includes listcontacttasks and getcontactdetails. The agent can pull the full history for any lead.

Q: What happens if the HighLevel API changes?

Pydantic AI catches it. If searchcontacts returns a schema that breaks your models, the framework throws a validation error instead of hallucinating a response.

Connect HighLevel to Pydantic AI to enforce strict runtime validation on every CRM contact, pipeline, and calendar operation.

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 Pydantic AI

Create your Vinkius account to connect HighLevel 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 HighLevel with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Pydantic AI contact validation

When your agent calls `create_contact`, Pydantic AI validates the required JSON body before the request leaves your server. Bad data ruins sales funnels. If the agent tries to send a malformed phone number, the framework fails loudly. You catch the error immediately instead of silently corrupting your CRM database via this MCP Server.

Pipeline state checks

Agents trigger `list_pipelines` to get the structure of your active deals. They need to know what exists before they act. Every response from the MCP endpoint gets mapped to your Pydantic models after running `search_opportunities`. If the API returns unexpected fields, the execution halts, ensuring your agent only operates on verified data structures.

Strict calendar booking

Your agent must read `list_calendars` and verify open times via `get_calendar_free_slots` before scheduling. Booking requires exact sequence execution. Once it finds a slot, it formats the `create_appointment` payload. The type-safe nature of Pydantic AI guarantees the date string matches the exact format HighLevel expects.

Setup guide

Set up HighLevel 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": {
        "highlevel-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent HighLevel 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 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 Pydantic AI

Use the MCPToolset class and pass your Vinkius HTTP endpoint. Inject it into your Agent using the toolsets parameter.

Yes. The server includes list_contact_tasks and get_contact_details. The agent can pull the full history for any lead.

Pydantic AI catches it. If search_contacts returns a schema that breaks your models, the framework throws a validation error instead of hallucinating a response.

Yes. Because Pydantic AI is model-agnostic, you can route your MCP tool calls through local LLMs or cloud providers like Anthropic.

The V8 Isolate Sandbox guarantees ephemeral execution. When your agent pulls schedules using get_calendar_free_slots, the memory allocates just long enough to pass the JSON back to your client, then vanishes entirely. No persistent storage exists.

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