How to Use the MasterGo MCP in Pydantic AI

Q: How do I set up Pydantic AI with my MasterGo MCP server?

Install pydantic-ai-slimmcp and then create an MCPToolset instance with your Vinkius server URL. Pass this toolset to your agent's constructor. It's a single line to get all the MasterGo tools ready to go.

Q: Can I use Pydantic AI to get a typed list of nodes from a MasterGo file?

Absolutely. When your agent calls listnodes, Pydantic AI will parse the output into a ListNode or a similar typed structure. This lets you iterate through the nodes in Python with autocomplete and type-checking.

Get type-safe, validated MasterGo data in your Python agent. Pydantic AI ensures every API call returns exactly what you expect.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MasterGo MCP to Pydantic AI

Create your Vinkius account to connect MasterGo 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 MasterGo with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Automation That Won't Break

Pydantic AI forces your agent's view of MasterGo to be correct. When your agent calls `get_file` or `list_projects`, the response is automatically parsed and validated against a Pydantic model. If the API ever returns something unexpected, you get an immediate `ValidationError`, not silent data corruption downstream. This means you can build scripts that depend on the exact structure of your design files. Use `list_nodes` to get a tree of components, and trust that the `id`, `name`, and `type` fields will always be there and have the right data type. Your code becomes simpler because you're not writing defensive checks everywhere.

Document Design Systems with Confidence

Create a script to pull your entire design system into structured objects. Your Pydantic AI agent can use `list_styles` to fetch all your color and typography tokens. The output isn't just a JSON blob; it's a list of typed objects you can work with directly in Python. Combine this with `get_comments` to pull all feedback on a file. Because every comment is a validated object, you can reliably build tools on top of it, like a script that automatically creates Jira tickets from comments tagged with "bug". It works because the data structure is guaranteed by the MCP server connection.

Trust Your MasterGo Data with Pydantic AI

This is about building dependable internal tools. Use your Pydantic AI agent to monitor team structures with `list_teams` and `get_org_members`. You can write a script to sync your MasterGo teams with an internal directory, and trust that it won't fail silently if a user's name is missing. The same goes for managing file history. When you call `get_file_versions`, you get a clean, typed list of versions. This lets you build reliable automations, like a weekly digest of design changes, without worrying about parsing messy API responses.

Setup guide

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

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

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

Install `pydantic-ai-slim[mcp]` and then create an `MCPToolset` instance with your Vinkius server URL. Pass this toolset to your agent's constructor. It's a single line to get all the MasterGo tools ready to go.

Pydantic AI automatically validates the JSON response from the tool against a predefined Pydantic model. If the response matches the expected structure and types, it returns a typed object. If not, it raises a `ValidationError` so you know immediately.

Absolutely. When your agent calls `list_nodes`, Pydantic AI will parse the output into a `List[Node]` or a similar typed structure. This lets you iterate through the nodes in Python with autocomplete and type-checking.

No, all the tools are read-only. Your agent can use tools like `get_file_versions` and `list_styles`, but it cannot alter the source design file. This protects your work from accidental changes by the agent.

The server acts as a secure proxy. It processes requests for your MasterGo design data—like file contents, comments, and node trees—but it doesn't retain any of it. Access is tied to your Vinkius token, and all communication is encrypted end-to-end.

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