How to Use the Framer MCP in Mastra AI

Q: Does this server support multi-step project discovery?

Absolutely. You can build a workflow that first calls listprojects to find the target site, retrieves details with getproject, and then lists the pages using listpages in a single run.

Build resilient, self-healing workflows that update your Framer CMS and publish pages using Mastra AI.

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 Mastra AI

Create your Vinkius account to connect Framer to Mastra 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build resilient CMS sync workflows with Mastra AI

Stop letting network hiccups break your content pipelines. This MCP Server integrates with Mastra's built-in workflow engine, allowing you to chain `list_collections` and `create_collection_item` with automatic exponential backoff. If the Framer API rate limits your request, Mastra pauses, retries, and keeps the pipeline moving. You don't have to write custom loop logic or error handlers to keep your external databases in sync.

Conditional publishing pipelines

Set up complex branching logic for your web deployments. Your Mastra agent can check the state of your layouts using `get_site_info` and decide whether to proceed with `publish_site` based on custom validation rules. If the layout check fails, the workflow routes to an administrative alert instead of deploying broken pages. This keeps your production environment safe from automated mistakes.

Human-in-the-loop CMS moderation

Prevent unauthorized content from going live on your web projects. Use Mastra's tool approval gate to pause execution right before your agent calls `create_collection_item`. Your team receives a Slack message or dashboard notification to review the generated text. Once approved, the workflow resumes and pushes the new record directly to Framer.

Setup guide

Set up Framer MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Framer tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "framer-mcp-client",
  servers: {
    "framer-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Framer Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Framer tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Framer transactions"
);
console.log(result.text);

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 Mastra AI

Initialize the MCPClient with your Vinkius endpoint URL. Spread the tools returned by listTools directly into your Mastra agent configuration to give it access to list_collections and create_collection_item.

Yes, you can configure Mastra's workflow engine to catch errors from publish_site. It will automatically retry the operation using exponential backoff if the Framer API is temporarily unavailable.

Enable the requireToolApproval option on your Mastra agent. This intercepts calls to create_collection_item, holding the execution until an operator confirms the payload is correct.

Absolutely. You can build a workflow that first calls list_projects to find the target site, retrieves details with get_project, and then lists the pages using list_pages in a single run.

Your Framer API credentials and CMS items are never stored or logged by the workflow engine. Vinkius manages the MCP transport security via an ephemeral sandbox, passing data directly to Framer without exposing your keys to third-party logs.

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