How to Use the CloudTalk MCP in OpenAI Agents SDK

Q: How do I connect CloudTalk to my OpenAI Agents SDK pipeline?

Instantiate MCPServerStreamableHttp with your Vinkius endpoint. Pass this server instance in the mcpservers list when initializing your Agent.

Q: Does the OpenAI Agents SDK cache the CloudTalk tool definitions?

Set cacheToolsList=True in your configuration. This prevents redundant schema lookups and keeps agent execution latency low.

Q: How does the agent handle failed calls or busy lines?

When makecall runs, the server returns the immediate API response. Your agent inspects this payload to log the failure or schedule a retry.

Trigger call center actions safely via MCP from your OpenAI Agents SDK workflows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CloudTalk MCP to OpenAI Agents SDK

Create your Vinkius account to connect CloudTalk to OpenAI Agents SDK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup CloudTalk with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run outbound dials directly from OpenAI Agents SDK

Let your agents dial customers directly using the `make_call` tool when specific triggers occur in your pipeline. You don't need to manually trigger dials or write custom API wrappers; the SDK discovers the MCP tools and executes the call. Your agent can pull the correct agent ID using `list_agents` and match it with the destination number. This keeps your human reps connected to active dials without context switching.

Safe contact synchronization via MCP Server

Run contact cleanups or updates with strict schema validation. Your agent can run `get_contact` to check current records and execute `update_contact` only when validation rules pass. If a customer requests deletion, the agent invokes `delete_contact` to wipe their data. The OpenAI dashboard traces this entire flow so you can audit every single deletion request.

Audit call records to route support tickets

Feed call logs directly into your agent routing loops. By calling `list_calls`, the agent reads past interactions and decides whether to escalate a ticket or schedule a callback. It filters the list by direction or agent to build a clean history timeline. You get the raw data directly from CloudTalk without writing custom polling scripts.

Setup guide

Set up CloudTalk MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all CloudTalk tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives CloudTalk tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate CloudTalk tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="CloudTalk Agent",
            instructions="You have access to CloudTalk tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by CloudTalk. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect CloudTalk now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about CloudTalk MCP in OpenAI Agents SDK

Instantiate `MCPServerStreamableHttp` with your Vinkius endpoint. Pass this server instance in the `mcp_servers` list when initializing your Agent.

Yes. You can restrict tool exposure at the agent definition level or handle it within your Vinkius console permissions.

Set `cacheToolsList=True` in your configuration. This prevents redundant schema lookups and keeps agent execution latency low.

When `make_call` runs, the server returns the immediate API response. Your agent inspects this payload to log the failure or schedule a retry.

Your contact phone numbers and call logs pass through an ephemeral V8 sandbox. No customer data is stored on Vinkius servers, keeping your customer records compliant.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript