How do I get my Framer API key?

Open your Framer project in the editor. Go to **Site Settings** (gear icon in the top bar), then navigate to the **General** tab. Scroll down to find the **Server API** section and click **Generate API key**. Copy the key and store it securely — treat it like a password. This key is specific to this project. Paste it into the configuration field below.

Can I push content from a spreadsheet into my Framer CMS?

Yes. Your AI agent can create and update CMS collection items programmatically. Describe the data you want to add, and it maps your fields to the Framer collection schema and creates the items — perfect for bulk content migrations or data-driven landing pages.

Does publishing through the API affect my Framer design?

No. The Server API only manages CMS content — it cannot modify your visual design, canvas layout, or component structure. Your designers remain in full control of the visual experience while content teams operate independently through the AI agent.

Is this suitable for agencies managing multiple Framer projects?

Yes. Each API key is bound to a specific Framer project. Configure separate integrations for each client project and your AI agent can switch between them — managing content across your entire portfolio without opening multiple browser tabs.

Framer MCP Server for Pydantic AI 8 tools — connect in under 2 minutes

Name: Framer
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 8 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Framer through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Framer "
            "(8 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Framer?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Framer MCP Server

Connect Framer to your AI agent and manage your website CMS content and publishing workflow conversationally.

Pydantic AI validates every Framer tool response against typed schemas, catching data inconsistencies at build time. Connect 8 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

CMS Collections — List, create, update, and manage CMS collection items directly from natural language commands.
Content Sync — Push content updates from external data sources into your Framer CMS collections programmatically.
Site Publishing — Trigger site publishes to push your latest CMS changes live.
Collection Schema — Query collection structures and field definitions to understand your content model.

The Framer MCP Server exposes 8 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Framer to Pydantic AI via MCP

Follow these steps to integrate the Framer MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 8 tools from Framer with type-safe schemas

Why Use Pydantic AI with the Framer MCP Server

Pydantic AI provides unique advantages when paired with Framer through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your Framer integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Framer connection logic from agent behavior for testable, maintainable code

Framer + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Framer MCP Server delivers measurable value.

Type-safe data pipelines: query Framer with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Framer tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Framer and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Framer responses and write comprehensive agent tests

Framer MCP Tools for Pydantic AI (8)

These 8 tools become available when you connect Framer to Pydantic AI via MCP:

create_collection_item

Create a new CMS item

get_project

Get project details

get_site_info

Get site configuration

list_collection_items

List items in a CMS collection

list_collections

List CMS collections

list_pages

List all site pages

list_projects

List all Framer projects

publish_site

This makes changes visible to visitors. Publish the website

Example Prompts for Framer in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Framer immediately.

"List all CMS collections in my Framer site."

"Add a new team member 'Ana Silva' to the Team Members collection."

"Publish my Framer site with the latest CMS changes."

Troubleshooting Framer MCP Server with Pydantic AI

Common issues when connecting Framer to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Framer + Pydantic AI FAQ

Common questions about integrating Framer MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer. your Framer MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.