Bring Omnichannel
to OpenAI Agents SDK
Learn how to connect Daktela 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 Daktela MCP Server?
Connect your Daktela omnichannel contact center to any AI agent and simplify how you coordinate customer support, track communication history, and manage CRM records through natural conversation.
What you can do
- Ticket Lifecycle — Create, list, and query support tickets and cases to ensure customer issues are resolved promptly.
- Omnichannel Activities — Monitor real-time and past activities across calls, emails, and chats within your center.
- CRM Control — List and create contacts and accounts (companies) to maintain an organized customer directory.
- Call & Email History — Retrieve detailed logs of past phone interactions and email threads for audit and reporting.
- Team & Queue Coordination — List configured queues and system users to manage agent distribution effectively.
- Profile Oversight — Fetch your authenticated user profile and verify system configurations directly from the agent.
How it works
1. Subscribe to this server
2. Enter your Daktela Domain and Access Token (found in your user settings)
3. Start managing your omnichannel communications from Claude, Cursor, or any MCP client
Who is this for?
- Support Team Leads — quickly check ticket statuses and monitor queue volumes via simple AI commands.
- Customer Service Agents — create CRM contacts and log activities directly from the workspace.
- Operations Managers — verify call history and retrieve agent distribution metadata via the AI assistant.
Built-in capabilities (12)
Create a new CRM contact
Create a new ticket
Get current user information
Get details of a specific ticket
List CRM accounts
List recent activities in Daktela
List call history
List CRM contacts
List email history
List contact center queues
List support tickets
List Daktela users
Why OpenAI Agents SDK?
The OpenAI Agents SDK auto-discovers all 12 tools from Daktela through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Daktela, 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
Daktela in OpenAI Agents SDK
Daktela and 3,400+ other MCP servers. One platform. One governance layer.
Teams that connect Daktela 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 Daktela in OpenAI Agents SDK
The Daktela 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
Daktela for OpenAI Agents SDK
Every tool call from OpenAI Agents SDK to the Daktela MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I see all the open tickets in my Daktela account?
Yes! Use the list_tickets tool. Your agent will retrieve the complete directory of support cases, which you can then filter or summarize.
How do I create a new contact in the Daktela CRM?
Use the create_contact action. Provide the first name, last name, and optional email or phone number to register the person in your CRM database instantly.
Is it possible to list the history of past phone calls via AI?
Absolutely. Use the list_call_history query. The agent will retrieve a detailed log of past voice interactions, including participants and durations.
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.
