How to Use the Makeswift MCP in Pydantic AI

Q: How do I initialize the Makeswift server in Pydantic AI?

Install pydantic-ai-slimmcp and set up the unified MCP toolset with your endpoint URL. You then pass this toolset into the toolsets array of your Agent instance.

Q: Why use Pydantic AI for Makeswift instead of a basic Python script?

The framework guarantees runtime correctness. If getpage returns a layout structure that doesn't match your expected Pydantic model, the agent halts immediately instead of pushing corrupt data.

Q: Can the agent check which domains are active?

The agent calls listhostnames to pull the active domain list. The framework ensures the returned URLs are parsed as valid string arrays before the agent processes them.

Give your Pydantic AI agents type-safe access to Makeswift so they can manage Next.js pages without silent failures.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Makeswift MCP to Pydantic AI

Create your Vinkius account to connect Makeswift 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 Makeswift with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage Makeswift pages with Pydantic AI

Agents that guess data structures break production environments. By connecting this MCP Server, your agent runs `list_pages` and validates the response directly against your Pydantic schemas. If a route is missing an expected field, the framework throws a loud validation error. This strictness applies to localized content as well. When the agent pulls `list_locales` or checks specific routing rules with `list_redirects`, you know exactly what format the data arrives in. Bad data never makes it into your downstream logic.

Validate React props via MCP Server

Marketers update content using predefined blocks, and those blocks have strict prop requirements. The agent executes `list_components` to pull the exact constraints for every widget in your workspace. Because Pydantic AI enforces correctness, the agent will not hallucinate missing props. It reads the exact schema, checks the environment using `get_site_details`, and ensures any generated content fits the actual React components perfectly.

Trigger and confirm content backups

You need proof that a backup actually finished before making changes. The agent triggers `create_snapshot` to capture the page state and immediately parses the response payload. It then follows up with `get_snapshot` to verify the exact timestamp and status. If you need a full audit, the agent pulls `list_snapshots`. Every step is strictly typed, so your automated backup pipeline never fails silently.

Setup guide

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

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

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

Install `pydantic-ai-slim[mcp]` and set up the unified MCP toolset with your endpoint URL. You then pass this toolset into the `toolsets` array of your Agent instance.

The framework guarantees runtime correctness. If `get_page` returns a layout structure that doesn't match your expected Pydantic model, the agent halts immediately instead of pushing corrupt data.

The agent calls `list_hostnames` to pull the active domain list. The framework ensures the returned URLs are parsed as valid string arrays before the agent processes them.

The MCP tools are model-agnostic. You can connect local models, OpenAI, or Anthropic, and they will all interact with `list_components` using the exact same type-safe constraints.

The integration specifically handles visual page layouts, text copy, and routing rules. When Pydantic AI queries this MCP server, it operates ephemerally, ensuring your agent only reads or modifies the exact workspace tied to your single endpoint token.

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