Bring Chatbot Orchestration
to OpenAI Agents SDK
Learn how to connect SmartChatAI to OpenAI Agents SDK and start using 12 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
What is the SmartChatAI MCP Server?
Connect your SmartChatAI account to any AI agent to automate your intelligent chatbot orchestration and lead collection. SmartChatAI provides a premier platform for building custom AI bots, and this integration allows you to retrieve chatbot metadata, manage knowledge bases via URL or PDF, and track conversational history through natural conversation.
What you can do
- Chatbot Orchestration — List all managed AI bots and retrieve detailed profile metadata, including status and configuration programmatically.
- Knowledge Base Lifecycle Management — Add new data sources (URL, PDF, Text) to your bots' knowledge base directly from the AI interface to ensure they are always informed.
- Message & Reply Control — Send automated replies and retrieve detailed chat history to maintain high-quality customer interactions via natural language.
- Web Scraper Automation — Trigger website scraping to ingest content into your AI models and ensure your bots have the latest information.
- Operational Monitoring — Track system health, manage webhooks, and monitor bot activity to ensure your conversational platform is always optimized.
How it works
1. Subscribe to this server
2. Enter your SmartChatAI API Key from your dashboard settings
3. Start managing your AI bots from Claude, Cursor, or any MCP-compatible client
Who is this for?
- Bot Developers — quickly update knowledge bases and test bot responses without switching tabs.
- Marketing Operations — automate the retrieval of lead data from chats and monitor bot engagement results via natural conversation.
- Customer Success Teams — streamline the retrieval of conversational logs and monitor user satisfaction directly within the chat.
Built-in capabilities (12)
Train bot using a PDF
Train bot using raw text
Train bot using a URL
Verify SmartChatAI API status
Requires a name and optional initial prompt. Provision a new AI agent
Get account profile
Retrieve conversation transcripts
Get configuration for a specific bot
List all AI chatbots
List active webhooks
Send a message and get AI reply
Discover and index domain links
Why OpenAI Agents SDK?
The OpenAI Agents SDK auto-discovers all 12 tools from SmartChatAI through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries SmartChatAI, 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
SmartChatAI in OpenAI Agents SDK
SmartChatAI and 3,400+ other MCP servers. One platform. One governance layer.
Teams that connect SmartChatAI 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 SmartChatAI in OpenAI Agents SDK
The SmartChatAI 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 12 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
SmartChatAI for OpenAI Agents SDK
Every tool call from OpenAI Agents SDK to the SmartChatAI 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 SmartChatAI API Key?
Log in to your SmartChatAI dashboard and you will find your unique secret API Key in the Settings or account management section.
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.