Hyperbrowser (Web Infra for AI) MCP Server for OpenAI Agents SDK 10 tools — connect in under 2 minutes
The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Hyperbrowser (Web Infra for AI) through the Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails — no manual schema definitions required.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
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="Hyperbrowser (Web Infra for AI) Assistant",
instructions=(
"You help users interact with Hyperbrowser (Web Infra for AI). "
"You have access to 10 tools."
),
mcp_servers=[mcp_server],
)
result = await Runner.run(
agent, "List all available tools from Hyperbrowser (Web Infra for AI)"
)
print(result.final_output)
asyncio.run(main())
* 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 Hyperbrowser (Web Infra for AI) MCP Server
Connect your Hyperbrowser account to any AI agent and take full control of your web automation and cloud browser infrastructure through natural conversation.
The OpenAI Agents SDK auto-discovers all 10 tools from Hyperbrowser (Web Infra for AI) through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns — chain multiple agents where one queries Hyperbrowser (Web Infra for AI), another analyzes results, and a third generates reports, all orchestrated through the Vinkius.
What you can do
- Managed Sessions — Create and manage remote headless browser sessions with built-in support for proxies, stealth mode, and specific browser versions
- AI Scraping — Trigger asynchronous scraping jobs that handle dynamic loading, retries, and CAPTCHAs automatically to retrieve clean HTML payloads
- Data Extraction — Use LLM-powered capabilities to extract structured data from any URL by simply providing a natural language prompt and optional JSON schema
- Visual Capture — Capture full-page screenshots of any rendered URL to audit visual changes or document web states accurately
- Remote Scripts — Execute custom JavaScript within active browser sessions to perform complex interactions or evaluate page states in real-time
- DOM Access — Retrieve raw, rendered HTML synchronously to process page content without managing complex scraping infrastructures
The Hyperbrowser (Web Infra for AI) 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 Hyperbrowser (Web Infra for AI) to OpenAI Agents SDK via MCP
Follow these steps to integrate the Hyperbrowser (Web Infra for AI) 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 Hyperbrowser (Web Infra for AI)
Why Use OpenAI Agents SDK with the Hyperbrowser (Web Infra for AI) MCP Server
OpenAI Agents SDK provides unique advantages when paired with Hyperbrowser (Web Infra for AI) 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
Hyperbrowser (Web Infra for AI) + OpenAI Agents SDK Use Cases
Practical scenarios where OpenAI Agents SDK combined with the Hyperbrowser (Web Infra for AI) MCP Server delivers measurable value.
Automated workflows: build agents that query Hyperbrowser (Web Infra for AI), process the data, and trigger follow-up actions autonomously
Multi-agent orchestration: create specialist agents — one queries Hyperbrowser (Web Infra for AI), another analyzes results, a third generates reports
Data enrichment pipelines: stream data through Hyperbrowser (Web Infra for AI) tools and transform it with OpenAI models in a single async loop
Customer support bots: agents query Hyperbrowser (Web Infra for AI) to resolve tickets, look up records, and update statuses without human intervention
Hyperbrowser (Web Infra for AI) MCP Tools for OpenAI Agents SDK (10)
These 10 tools become available when you connect Hyperbrowser (Web Infra for AI) to OpenAI Agents SDK via MCP:
create_session
Returns a connection URL and session details. Pass optional JSON config for proxy, stealth, browser version, etc. Create a new Hyperbrowser remote session
extract_data
g., "Extract product name and price"). Optionally pass JSON schema. The platform will render, extract, and return clean JSON. Use Hyperbrowser LLM capabilities to extract structured data
get_scrape_job
When status is completed, the response will contain the HTML payload and metadata. Get status/results of a Hyperbrowser scraping job
get_session
Returns duration, connection endpoints, and current health/status. Get status of a specific Hyperbrowser session
list_sessions
Pass optional status (active, completed, failed) to filter. List active or past Hyperbrowser sessions
page_content
Get raw HTML content synchronously via Hyperbrowser
page_screenshot
Returns image metadata or URL. Take a managed screenshot via Hyperbrowser
run_script
The browser will execute and return the evaluation result. Execute JS script inside a running Hyperbrowser session
start_scrape
Returns a job ID. Use get_scrape_job to poll for completion. Pass target URL and optional JSON config. Start a Hyperbrowser async scraping job
stop_session
Terminate an active Hyperbrowser session
Example Prompts for Hyperbrowser (Web Infra for AI) in OpenAI Agents SDK
Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Hyperbrowser (Web Infra for AI) immediately.
"Extract the latest pricing and features from 'https://example.com/pricing'"
"Take a full-page screenshot of 'https://news.ycombinator.com'"
"List all my active Hyperbrowser sessions"
Troubleshooting Hyperbrowser (Web Infra for AI) MCP Server with OpenAI Agents SDK
Common issues when connecting Hyperbrowser (Web Infra for AI) to OpenAI Agents SDK through the Vinkius, and how to resolve them.
MCPServerStreamableHttp not found
pip install --upgrade openai-agentsAgent not calling tools
Hyperbrowser (Web Infra for AI) + OpenAI Agents SDK FAQ
Common questions about integrating Hyperbrowser (Web Infra for AI) MCP Server with OpenAI Agents SDK.
How does the OpenAI Agents SDK connect to MCP?
MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.Can I use multiple MCP servers in one agent?
MCPServerSse instances to the agent constructor. The agent can use tools from all connected servers within a single run.Does the SDK support streaming responses?
Connect Hyperbrowser (Web Infra for AI) with your favorite client
Step-by-step setup guides for every MCP-compatible client and framework:
Anthropic's native desktop app for Claude with built-in MCP support.
AI-first code editor with integrated LLM-powered coding assistance.
GitHub Copilot in VS Code with Agent mode and MCP support.
Purpose-built IDE for agentic AI coding workflows.
Autonomous AI coding agent that runs inside VS Code.
Anthropic's agentic CLI for terminal-first development.
Python SDK for building production-grade OpenAI agent workflows.
Google's framework for building production AI agents.
Type-safe agent development for Python with first-class MCP support.
TypeScript toolkit for building AI-powered web applications.
TypeScript-native agent framework for modern web stacks.
Python framework for orchestrating collaborative AI agent crews.
Leading Python framework for composable LLM applications.
Data-aware AI agent framework for structured and unstructured sources.
Microsoft's framework for multi-agent collaborative conversations.
Connect Hyperbrowser (Web Infra for AI) to OpenAI Agents SDK
Get your token, paste the configuration, and start using 10 tools in under 2 minutes. No API key management needed.