Bring Rpa
to OpenAI Agents SDK
Learn how to connect Cloud BOT 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 Cloud BOT MCP Server?
Connect your Cloud BOT account to any AI agent and take full control of your cloud-based Robotic Process Automation (RPA) and browser-based workflows through natural conversation.
What you can do
- Robot Orchestration — List and manage all browser automation robots in your account programmatically, retrieving detailed configuration and input parameter metadata
- Automated Job Execution — Programmatically trigger bot executions with custom JSON parameters to coordinate high-fidelity web scraping and data entry tasks
- Workflow Monitoring — Track the real-time status of your automation jobs and retrieve detailed logs and results to maintain perfectly coordinated RPA operations
- File Architecture — Access and manage files within the Cloud BOT storage used or generated by your robots to maintain high-fidelity data cycles
- Lifecycle Management — Programmatically cancel or suspend running jobs and verify API connectivity directly through your agent for instant operational reporting
How it works
1. Subscribe to this server
2. Retrieve your Access Token, Secret Key, and Public ID from the Cloud BOT dashboard (API settings)
3. Start automating your web-based workflows from Claude, Cursor, or any MCP client
No more manual logging into individual bot portals to check job progress. Your AI acts as your dedicated RPA engineer and browser automation coordinator.
Who is this for?
- Operations Teams — instantly trigger data extraction bots and check execution histories using natural language commands
- Growth Marketers — automate lead generation and web monitoring tasks without leaving your workspace
- Developers & Ops — integrate high-speed browser automation into custom workflows through simple AI queries
Built-in capabilities (7)
Cancel a running job
You can pass optional input parameters as a JSON string. Trigger a bot execution
Get details for a specific bot
Check the status of a job
List all available RPA bots
List files in Cloud BOT storage
List recent execution jobs
Why OpenAI Agents SDK?
The OpenAI Agents SDK auto-discovers all 7 tools from Cloud BOT through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Cloud BOT, 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
Cloud BOT in OpenAI Agents SDK
Cloud BOT and 3,400+ other MCP servers. One platform. One governance layer.
Teams that connect Cloud BOT 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 Cloud BOT in OpenAI Agents SDK
The Cloud BOT 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
Cloud BOT for OpenAI Agents SDK
Every tool call from OpenAI Agents SDK to the Cloud BOT 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 find my Cloud BOT API credentials?
Log in to your account, navigate to the API Settings section, and you will find your Access Token, Secret Key, and Public ID.
Can I pass custom parameters to a bot?
Yes! The execute_bot tool accepts a params_json string where you can provide a JSON object matching your bot's input configuration.
How do I check the results of an automation?
Use the get_job_status tool with a job ID to retrieve the execution status and any outputs or files generated by the bot.
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.