Bring Proxy Management
to OpenAI Agents SDK
Learn how to connect Bright Data to OpenAI Agents SDK and start using 10 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
GDPR Free for SubscribersCompatible with every major AI agent and IDE
Gemini
What is the Bright Data MCP Server?
Connect your Bright Data account to any AI agent to automate complex web data extraction, bypass sophisticated anti-bot systems, and manage your proxy infrastructure through natural language.
What you can do
- Web Unlocking & SERP — Use the
send_requesttool to bypass anti-bot protections or extract structured data from search engines using Web Unlocker or SERP API zones. - Dataset Orchestration — Trigger large-scale data collections with
trigger_dataset, monitor progress withget_dataset_progress, and download snapshots once ready. - Browser Management — List and monitor active Scraping Browser sessions to debug or track automated browser workflows.
- Infrastructure Control — Retrieve all configured zones, check account status, and fetch proxy credentials (passwords) for specific zones securely.
- Marketplace Discovery — Browse available datasets in the Bright Data marketplace to find pre-collected data for your industry.
How it works
- Subscribe to this server
- Enter your Bright Data API Key
- Start scraping and managing proxies from Claude, Cursor, or any MCP-compatible client
Your AI now acts as a data engineer, capable of retrieving real-time web information even from the most protected sources.
Who is this for?
- Data Scientists & Analysts — Automate the collection of training data or market intelligence without manual script execution.
- Developers — Debug scraping browser sessions and manage proxy zones directly from the code editor.
- Market Researchers — Extract structured SERP data to track rankings and competitor movements via simple conversation.
Built-in capabilities (10)
Check account status
Get all zones
Monitor dataset snapshot progress
Download a dataset snapshot
Get specific zone info
Get zone passwords
List Scraping Browser sessions
List available datasets in the marketplace
Send a request to Unlocker or SERP API
Trigger a dataset collection (Crawl API)
Why OpenAI Agents SDK?
The OpenAI Agents SDK auto-discovers all 10 tools from Bright Data through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Bright Data, another analyzes results, and a third generates reports, all orchestrated through Vinkius.
- —
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
Bright Data in OpenAI Agents SDK
Bright Data and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Bright Data to OpenAI Agents SDK through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 4,000+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for Bright Data in OpenAI Agents SDK
The Bright Data 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. All 10 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in OpenAI Agents SDK only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.
* 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
How Vinkius secures
Bright Data for OpenAI Agents SDK
Every tool call from OpenAI Agents SDK to the Bright Data MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
How do I bypass anti-bot systems on a specific website?
Use the send_request tool and specify a zone configured with Web Unlocker. Provide the target URL, and Bright Data will handle the rotation and headers to return the content.
Can I check if my data collection is finished?
Yes. Use the get_dataset_progress tool with your Snapshot ID. It will return the current percentage and status of the extraction process.
How do I get the proxy credentials for my scraper?
You can use the get_zone_passwords tool by providing the zone name. This will retrieve the necessary passwords for proxy authentication.
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.
Can I use multiple MCP servers in one agent?
Yes. Pass a list of 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?
Yes. The SDK supports SSE and Streamable HTTP transports, both of which work natively with Vinkius.
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.
Explore More MCP Servers
View all →
BookStack (Wiki)
32 toolsManage your BookStack wiki directly from your AI agent — search, read, create, and organize pages, chapters, and books with ease.
Shippify
11 toolsAutomate logistics and last-mile delivery via Shippify — manage deliveries, tracking, and warehouses directly from any AI agent.
Glean
10 toolsEmpower enterprise search via Glean — search across all SaaS apps, retrieve AI answers, manage custom indexing, and handle chat directly from any AI agent.
Facebook Pages
12 toolsManage your Facebook Pages via AI — publish posts, list feed, track insights, and engage with comments directly through your agent.