How to Use the Framer MCP in Pydantic AI

Q: Can I use pydantic-ai to publish a Framer site?

Yes, the agent can call publishsite as a validated tool. You can wrap the agent in a run loop to inspect the output before making changes live.

Write type-safe Python code to manage Framer CMS collections and publish site updates using pydantic-ai and MCP.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Framer MCP to Pydantic AI

Create your Vinkius account to connect Framer 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 Framer with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe Framer MCP Server updates with validation

Don't let silent API failures corrupt your production site during automated edits. This toolset validates payloads against strict models before calling `create_collection_item`. When fetching existing content with `list_collection_items`, pydantic-ai ensures the returned JSON matches your expected Python types. If Framer changes its API structure, your code fails loudly instead of corrupting data.

Programmatic page and site discovery

Let your agent inspect your site structure with absolute certainty by calling `list_pages` to map out your layout. The agent parses the results into typed Python objects. By using `get_site_info` and `list_collections`, your agent builds a clear map of your content structure. This makes it easy to write scripts that verify layout settings before pushing live changes.

Secure, structured publishing workflows

Automate your deployment pipeline without guessing by discovering target projects using `list_projects`. The agent fetches details via `get_project` using type-safe schemas. Once the validation checks pass, the agent triggers `publish_site`. Because pydantic-ai is model-agnostic, you can run this entire safe workflow using OpenAI, Anthropic, or local models.

Setup guide

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

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

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

Use MCPToolset with your Vinkius HTTP URL, then pass it to the toolsets argument of your Agent. Do not use the deprecated MCPServerHTTP class.

The SDK raises a validation error immediately. This prevents your agent from acting on corrupt or hallucinated data when querying list_collection_items.

Yes, the agent can call publish_site as a validated tool. You can wrap the agent in a run loop to inspect the output before making changes live.

Yes, pydantic-ai is model-agnostic. You can run local models to process data from get_site_info and execute updates.

Your CMS text and fields are transmitted over TLS directly between your agent and the Framer API. Vinkius operates a zero-trust sandbox that never logs or inspects the content of create_collection_item payloads.

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