Can I take a full-page screenshot using the agent?

Yes! Use the `take_screenshot` tool and in the `options` field, provide a JSON string like `{"fullPage": true}`. Browserless will capture the entire length of the page.

How do I convert a web page to a PDF?

Simply ask the agent to `generate_pdf` and provide the URL. It will use Browserless to render the page and return the generated PDF file (usually as a binary response or link).

Does the integration allow scraping specific data fields?

Yes. Use the `run_scrape` action and provide the URL along with an `elements` array containing the selectors and names for the data you want to extract.

Browserless MCP Server for OpenAI Agents SDK 8 tools — connect in under 2 minutes

Name: Browserless
Availability: InStock
Author: Vinkius

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

Built by Vinkius GDPR 8 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Browserless through the 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="Browserless Assistant",
            instructions=(
                "You help users interact with Browserless. "
                "You have access to 8 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Browserless"
        )
        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 Browserless MCP Server

Connect your Browserless.io account to any AI agent and orchestrate your headless Chrome operations, web automation, and document generation through natural conversation.

The OpenAI Agents SDK auto-discovers all 8 tools from Browserless through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns — chain multiple agents where one queries Browserless, another analyzes results, and a third generates reports, all orchestrated through the Vinkius.

What you can do

Visual Captures — Take high-quality screenshots of any URL with advanced options like full-page capture.
Document Generation — Convert any web page into a polished PDF document directly from your workspace.
Rendered Content — Retrieve the fully rendered HTML content of JavaScript-heavy websites.
Custom Scraping — Run targeted scraping requests by providing element selectors to extract specific data.
Infrastructure Monitoring — Monitor active sessions, retrieve usage statistics, and check the health of the Browserless service.
Configuration Access — Access and verify your account configuration and limits using natural language.

The Browserless MCP Server exposes 8 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 Browserless to OpenAI Agents SDK via MCP

Follow these steps to integrate the Browserless 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 8 tools from Browserless

Why Use OpenAI Agents SDK with the Browserless MCP Server

OpenAI Agents SDK provides unique advantages when paired with Browserless 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

Browserless + OpenAI Agents SDK Use Cases

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

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

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

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

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

Browserless MCP Tools for OpenAI Agents SDK (8)

These 8 tools become available when you connect Browserless to OpenAI Agents SDK via MCP:

check_system_health

Check the health of the Browserless service

generate_pdf

Generate a PDF of a URL

get_account_config

Retrieve account configuration

get_page_content

Retrieve the rendered HTML content of a URL

get_usage_stats

Retrieve account usage statistics

list_active_sessions

List currently active browser sessions

run_scrape

Run a custom scraping script

take_screenshot

Take a screenshot of a URL using headless Chrome

Example Prompts for Browserless in OpenAI Agents SDK

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

"Take a full-page screenshot of https://news.ycombinator.com."

"Generate a PDF of the article at https://example.com/blog/post-1."

"Scrape the titles of all products on https://example.com/shop."

Troubleshooting Browserless MCP Server with OpenAI Agents SDK

Common issues when connecting Browserless 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.

Browserless + OpenAI Agents SDK FAQ

Common questions about integrating Browserless 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.