Bring Data Extraction
to OpenAI Agents SDK
Learn how to connect Apify to OpenAI Agents SDK and start using 7 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
What is the Apify MCP Server?
Connect your Apify account to any AI agent and simplify how you manage your web scraping, automation actors, and data storage through natural conversation.
What you can do
- Actor Control — List and trigger serverless actors for web scraping and automation directly from your agent.
- Dataset Retrieval — Fetch the resulting data records (items) from your datasets to analyze or process values via AI.
- Run Monitoring — Track the history and status of recent actor executions to ensure reliability.
- Task Management — List and query configured actor tasks to reuse saved scraper settings.
- Data Insights — Retrieve detailed metadata and logs for specific runs to debug complex automations.
- Storage Visibility — List all datasets in your account to manage your collected web data.
How it works
1. Subscribe to this server
2. Enter your Apify API Token (found in your account settings under Integrations)
3. Start running your scrapers from Claude, Cursor, or any MCP client
Who is this for?
- Data Scientists & Researchers — quickly retrieve scraped data from datasets and analyze trends via simple AI commands.
- Automation Engineers — trigger actor runs and monitor execution health directly from the workspace.
- Product Managers — get instant bird's-eye views of automated data collection tasks and results.
Built-in capabilities (7)
Get items from a dataset
Get details for a specific run
List recent actor executions
List configured actor tasks
List Apify actors
List Apify datasets
Trigger an actor run
Why OpenAI Agents SDK?
The OpenAI Agents SDK auto-discovers all 7 tools from Apify through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Apify, 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
Apify in OpenAI Agents SDK
Apify and 3,400+ other MCP servers. One platform. One governance layer.
Teams that connect Apify 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 | 3,400+ 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 Apify in OpenAI Agents SDK
The Apify 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 7 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
Apify for OpenAI Agents SDK
Every tool call from OpenAI Agents SDK to the Apify MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I provide input parameters when running an actor?
Yes! Use the run_actor tool and provide the optional input JSON object to configure specific scraper settings for that run.
How do I see the items collected in a dataset?
Run the get_dataset_results query with your Dataset ID. The agent will retrieve the data records, which you can then ask the AI to summarize or analyze.
Is it possible to check the status of a specific actor run?
Absolutely. Use the get_run_details tool and provide the Run ID. Your agent will retrieve the status (RUNNING, SUCCEEDED, FAILED) and metadata for that specific execution.
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.