Can I trigger a browser task with a different starting URL?

Yes! Use the `run_task` tool and provide the Task ID. In the `overrides` field, you can pass a JSON object like `{"url": "https://newsite.com"}` to change the starting point dynamically.

How do I see the screenshot captured by a task?

Simply ask the agent to `get_run` and provide the Run ID. Once the status is 'finished', the response will include a `screenshot_url` that you can click to view the image.

Does the integration allow taking a quick screenshot without a saved task?

Yes. Use the `take_screenshot` action and provide the URL. It will create a simplified run that captures the page and returns the result URL once processed.

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

Name: Browserbear
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 Browserbear 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="Browserbear Assistant",
            instructions=(
                "You help users interact with Browserbear. "
                "You have access to 10 tools."
            ),
            mcp_servers=[mcp_server],
        )

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

Connect your Browserbear (Roborabbit) account to any AI agent and orchestrate your browser automation, web scraping, and visual monitoring workflows through natural conversation.

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

What you can do

Task Oversight — List and retrieve detailed metadata for all your saved browser automation tasks.
Automation Execution — Trigger task runs with dynamic overrides (like URL or form data) and monitor their progress.
Visual Captures — Take high-quality screenshots of any URL with customizable dimensions and wait times.
Data Extraction — Retrieve scraped structured data and screenshot URLs directly into your workspace.
Run Management — List, inspect, and delete history of your automation runs.
Project Coordination — Access and organize your tasks across multiple projects and track account usage.

The Browserbear 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 Browserbear to OpenAI Agents SDK via MCP

Follow these steps to integrate the Browserbear 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 Browserbear

Why Use OpenAI Agents SDK with the Browserbear MCP Server

OpenAI Agents SDK provides unique advantages when paired with Browserbear 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

Browserbear + OpenAI Agents SDK Use Cases

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

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

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

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

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

Browserbear MCP Tools for OpenAI Agents SDK (10)

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

create_task

Create a new browser automation task

delete_run

Delete a task run record

get_account_usage

Retrieve account usage statistics

get_run

Get status and results of a task run

get_task

Get details of a specific task

list_projects

List all projects in the account

list_runs

List all task runs

list_tasks

List all browser automation tasks

run_task

Trigger a run for a specific task

take_screenshot

Take a quick screenshot of a URL

Example Prompts for Browserbear in OpenAI Agents SDK

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

"List all my browser automation tasks."

"Take a screenshot of https://vinkius.com at 1280x800 resolution."

"Run task task_123 and override the starting URL to https://google.com."

Troubleshooting Browserbear MCP Server with OpenAI Agents SDK

Common issues when connecting Browserbear 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.

Browserbear + OpenAI Agents SDK FAQ

Common questions about integrating Browserbear 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.