How to Use the MakePlans MCP in Pydantic AI

Q: How do I install MakePlans into Pydantic AI?

Run pip install "pydantic-ai-slimmcp". Initialize an MCPToolset with your endpoint URL, then pass it as a list to the toolsets parameter in your Agent setup.

Q: What happens if MakePlans returns unexpected data to Pydantic AI?

The framework fails loudly. If listappointments returns a structure that violates your Pydantic model, the agent halts execution instead of passing corrupt data to the user.

Q: Do I use MCPServerHTTP for MakePlans in Pydantic AI?

No. That class is deprecated. You use the unified MCPToolset approach, which supports both Streamable HTTP and SSE transports natively.

Q: Can Pydantic AI filter MakePlans resources?

Your agent handles the filtering logic. It calls listbookingresources, validates the returned list against your schema, and then applies Python logic to sort or filter the valid records.

Enforce strict typing on MakePlans MCP Server. Catch API schema errors instantly when your Pydantic AI agent books appointments.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MakePlans MCP to Pydantic AI

Create your Vinkius account to connect MakePlans 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 MakePlans with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate MakePlans responses at runtime

The `get_appointment_details` tool returns specific JSON structures from the scheduling API. Pydantic AI intercepts this payload and forces it through your defined data models. If a date string is missing or malformed, the framework throws a validation error immediately. This prevents silent failures down the line. Your agent won't hallucinate missing `person_id` values because the system rejects bad data before the LLM even sees it. You get guaranteed correctness over speed.

Execute exact booking payloads

The `create_new_appointment` tool strictly requires `person_id`, `service_id`, and `start_at` parameters. Pydantic AI ensures the LLM constructs this exact payload before dispatching the request to the external server. You set this up by passing `MCPToolset("http://...")` to your Agent constructor. The framework handles the underlying HTTP transport while demanding absolute type compliance for every parameter passed to `create_new_customer` or other write operations.

Swap LLMs without breaking the scheduling logic

The `find_available_slots` tool requires a `service_id` and a date range. Because Pydantic AI is model-agnostic, you switch from OpenAI to a local model without rewriting your integration. The framework enforces the schema regardless of the backend. Your agent logic stays focused on querying `list_available_services` and matching user intent. The Pydantic layer translates the LLM's output into the exact format required by the MakePlans REST API.

Setup guide

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

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

result = await agent.run("List recent MakePlans 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 MakePlans. 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 MakePlans 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 MakePlans MCP in Pydantic AI

Run `pip install "pydantic-ai-slim[mcp]"`. Initialize an `MCPToolset` with your endpoint URL, then pass it as a list to the `toolsets` parameter in your Agent setup.

The framework fails loudly. If `list_appointments` returns a structure that violates your Pydantic model, the agent halts execution instead of passing corrupt data to the user.

No. That class is deprecated. You use the unified `MCPToolset` approach, which supports both Streamable HTTP and SSE transports natively.

Your agent handles the filtering logic. It calls `list_booking_resources`, validates the returned list against your schema, and then applies Python logic to sort or filter the valid records.

The server handles personally identifiable information like customer names and schedule dates. Vinkius manages this securely by running the integration in an ephemeral sandbox, ensuring data passes straight to your client without resting on our infrastructure.

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