How to Use the Magicplan MCP in Pydantic AI

Enforce strict type validation for Magicplan data using Pydantic AI and this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Magicplan MCP to Pydantic AI

Create your Vinkius account to connect Magicplan 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 Magicplan with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe Magicplan data for Pydantic AI

Every response from `get_project_details` or `get_plan_measurements` is validated against your Pydantic models. If the data structure deviates, the agent halts immediately to prevent corruption. This ensures your agent works with clean, predictable data. You define the schema, and the framework enforces it at runtime every time the tool runs.

Financial data validation with Pydantic AI

Your agent retrieves estimates using `list_project_estimates` and `get_estimate_details` with full type verification. You catch unexpected API changes before they impact your financial logic. This adds a layer of safety when handling project costs. Your agent only proceeds if the financial data matches your strict internal requirements.

Form and user data integrity in your agent

Use `list_available_forms` and `get_plan_form_data` to ensure your agent handles site documentation correctly. Pydantic AI validates every field returned from the server. This approach prevents your agent from processing malformed form submissions. It validates user lists from `list_workspace_users` to ensure only authorized entities are processed.

Setup guide

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

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

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

You install the MCP-enabled version of the library and pass the server URL to the MCPToolset. It handles the connection and provides the tools to your agent.

The framework triggers a validation error immediately. Your agent won't hallucinate or crash because it treats the data as invalid input.

Yes, the framework is model-agnostic. You can pair it with local models or cloud-based ones while maintaining strict type validation.

It uses standard HTTP or SSE transports. You need a running server instance that the framework can reach via the provided URL.

The server requires your endpoint token for authentication. Your data remains isolated within your specific workspace environment.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.