Can my AI read the strict structure of a custom model before creating a block?

Yes! We highly recommend asking your agent to use `get_model_schema` first. By retrieving the exact JSON fields (Strings, Lists, Booleans), the AI naturally learns the shape of your `Page` or `HeroContent` model and formats its `create_visual_block` mutation flawlessly avoiding validation errors.

How can I count how many blogs or pages are in my Builder space?

You can use the native `count_model_entities` tool. By querying a model like `blog-post`, the agent accesses the Builder backend with `limit=1` exclusively to extract the metadata counts without downloading heavyweight content arrays—highly efficient for broad analytics.

Can the agent wipe an accidentally created page completely?

Yes. If an error occurs or a staging draft needs removal, the agent can call `wipe_visual_block`. Supply the targeted entity ID, and the HTTP DELETE command is irreversibly broadcasted to the Builder environment. Always review IDs manually.

Builder MCP Server for OpenAI Agents SDK 10 tools — connect in under 2 minutes

Name: Builder
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 10 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Builder through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.

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 agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp

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

        agent = Agent(
            name="Builder Assistant",
            instructions=(
                "You help users interact with Builder. "
                "You have access to 10 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Builder"
        )
        print(result.final_output)

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 Builder MCP Server

Connect your Builder.io space to any AI agent and take full programmatic control over your headless CMS architecture and visual pages through natural conversation.

The OpenAI Agents SDK auto-discovers all 10 tools from Builder through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Builder, another analyzes results, and a third generates reports, all orchestrated through Vinkius.

What you can do

Content Automation — Create, update, or wipe specific content entries across any data model dynamically
Schema Navigation — List your active Builder models and analyze exact field definitions and strict JSON bounds
Search & Retrieval — Use query strings to pull matched content documents or count entities effortlessly
Media Fetching — Inspect metadata and URLs of uploaded assets living on the Builder platform
Headless Maintenance — Delete deprecated components or page sections instantly using targeted endpoints

The Builder MCP Server exposes 10 tools through the Vinkius. Connect it to OpenAI Agents SDK 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 Builder to OpenAI Agents SDK via MCP

Follow these steps to integrate the Builder MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 10 tools from Builder

Why Use OpenAI Agents SDK with the Builder MCP Server

OpenAI Agents SDK provides unique advantages when paired with Builder through the Model Context Protocol.

Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

Builder + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the Builder MCP Server delivers measurable value.

Automated workflows: build agents that query Builder, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents. one queries Builder, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through Builder tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query Builder to resolve tickets, look up records, and update statuses without human intervention

Builder MCP Tools for OpenAI Agents SDK (10)

These 10 tools become available when you connect Builder to OpenAI Agents SDK via MCP:

count_model_entities

Quickly count the number of live items stored within a specific model

create_visual_block

Create new content entries or visual blocks inside a Builder model

get_media_file

Retrieve details about an uploaded media asset within Builder.io

get_model_schema

Get the exact field structure and schema definitions for a single model

get_single_content

g. `query.data.title=Home`). Retrieve a specific content document by query matching from Builder.io

list_builder_models

List all defined data models and schemas in the Builder space

list_model_content

Useful for fetching dynamic content blocks or pages. Retrieve a list of content entries for a specific Builder.io model

search_active_models

Find Builder models matching a specific criteria or substring

update_visual_block

Update an existing Builder.io content block or document

wipe_visual_block

Permanently delete a specific content entry from Builder.io

Example Prompts for Builder in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Builder immediately.

"List all active Builder models in my workspace."

"Fetch the schema for the 'custom-hero' model."

"Find a page with the title "Home" on the 'page' model."

Troubleshooting Builder MCP Server with OpenAI Agents SDK

Common issues when connecting Builder to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

Builder + OpenAI Agents SDK FAQ

Common questions about integrating Builder MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.