How to Use the Framer MCP in OpenAI Agents SDK

Q: How does OpenAI Agents SDK handle Framer CMS collection schemas?

The agent calls listcollections to dynamically read your schema. It then formats the payload for createcollectionitem based on those exact fields, avoiding hardcoded structures.

Q: Can I trace Framer tool calls in my monitoring dashboard?

Every time your agent calls listcollectionitems or getsiteinfo, the execution trace appears in your OpenAI dashboard. This makes debugging agent decisions simple.

Let your OpenAI Agents SDK connect to this Framer MCP Server to sync production CMS data and publish live pages directly.

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 OpenAI Agents SDK

Create your Vinkius account to connect Framer to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Framer CMS items with OpenAI Agents SDK

This MCP Server exposes `create_collection_item` to push structured content straight into your Framer collections from any Python script. Your agent reads your existing setup using `list_collections` to figure out where the data belongs without hardcoded configurations. Because you are using the OpenAI Agents SDK, you can set up guardrails that intercept these calls before they hit your live site. The agent checks current items with `list_collection_items`, drafts the new post, and waits for your confirmation if the safety rules trigger.

Orchestrate multi-agent site publishing

Let specialized agents split the work using `list_pages` to read site layouts and draft updates. A supervisor agent runs `publish_site` only when all checks pass. This MCP setup handles handoffs smoothly within your Python runtime. You track every single API payload and tool call directly inside your OpenAI dashboard for complete visibility.

Inspect Framer workspace structure on the fly

Your agent needs to know what it's working on, so it uses `list_projects` to find your target workspace. It calls `get_project` to pull the precise structure of your layout. The OpenAI Agents SDK caches these tools when you set `cacheToolsList=True` to speed up execution. This prevents redundant network requests when fetching site details via `get_site_info`.

Setup guide

Set up Framer MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Framer tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Framer tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Framer tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Framer Agent",
            instructions="You have access to Framer tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install openai-agents and initialize MCPServerStreamableHttp pointing to your Vinkius endpoint. Pass the server object into the mcp_servers list when instantiating your Agent.

Yes, by using the SDK's built-in guardrails. You write a validation function that inspects the tool call before the agent actually triggers the live publish.

The agent calls list_collections to dynamically read your schema. It then formats the payload for create_collection_item based on those exact fields, avoiding hardcoded structures.

Every time your agent calls list_collection_items or get_site_info, the execution trace appears in your OpenAI dashboard. This makes debugging agent decisions simple.

Your Framer API tokens are stored securely in Vinkius's isolated sandbox and never exposed to the LLM. The agent only sees the clean JSON outputs from tools like list_projects and never touches the raw credentials.

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