How to Use the DeveloperHub MCP in OpenAI Agents SDK

Build production documentation agents with the OpenAI Agents SDK. Guardrails and full tracing included.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DeveloperHub MCP to OpenAI Agents SDK

Create your Vinkius account to connect DeveloperHub 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 DeveloperHub with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Audit Docs Without The Risk

Your agent can scan for outdated content using `list_recently_updated_pages` and `get_documentation_page_content`. The OpenAI Agents SDK lets you build guardrails to approve any changes before your agent acts, preventing accidental public-facing errors. This is how you use automation responsibly. Let the agent find problems, but keep a human in the loop for the final say. It's the right way to manage a production documentation portal.

Delegate Tasks with Multi-Agent Handoffs

Use one agent to monitor changes with `list_product_changelogs` and hand off findings to another. A 'tracker' agent can watch for updates, while a 'writer' agent drafts new content based on the changelog. This is a core strength of the OpenAI SDK. This MCP server gives your agents the specific tools they need to focus. The SDK's handoff feature makes this clean, letting each agent do one thing well instead of building one monolithic agent that does everything poorly.

Trace Every OpenAI Agents SDK Action

Know exactly what your agent is doing inside DeveloperHub. Every call to tools like `search_documentation_portal` or `get_documentation_sitemap` is traced in your OpenAI dashboard. No more black boxes. You get a full, undeniable audit trail. That's not a nice-to-have; it's a requirement for any serious production system that touches your customer-facing docs.

Setup guide

Set up DeveloperHub 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 DeveloperHub tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate DeveloperHub 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="DeveloperHub Agent",
            instructions="You have access to DeveloperHub 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 DeveloperHub. 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 DeveloperHub 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 DeveloperHub MCP in OpenAI Agents SDK

It's simple. You pass the MCP Server endpoint URL from Vinkius to `MCPServerStreamableHttp`. The SDK handles the tool discovery automatically so your agent knows what it can do.

Yes. While the SDK discovers all tools from the MCP toolset, you can implement custom guardrails in your agent's code to restrict access. This lets you block destructive actions or limit agents to read-only functions like `list_documentation_projects`.

Create a dedicated monitoring agent. Have it periodically call `list_recently_updated_pages` and `list_product_changelogs`. Use the SDK's built-in tracing to log which pages are flagged, creating a persistent record for your team to review.

No. Your Vinkius endpoint token handles all authentication for this MCP server. The SDK just needs the URL, and Vinkius manages the connection securely.

The server only touches your DeveloperHub data: documentation content, project names, changelogs, and sitemaps. Your OpenAI credentials and agent logic stay separate. Vinkius sandboxes each connection, so this toolset only sees what you allow it to see in DeveloperHub.

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