How to Use the CallPage MCP in OpenAI Agents SDK

Q: How do I connect CallPage to OpenAI Agents SDK?

Initialize MCPServerStreamableHttp with your Vinkius endpoint URL. Pass it to your Agent constructor using the mcpservers parameter. Set cacheToolsList=True to speed up tool discovery on boot.

Q: Can OpenAI Agents SDK read my CallPage recordings?

Yes, the listcalls tool returns the recording URLs for your callbacks. Your agent can pass these URLs to a transcription model. The SDK traces exactly when the agent accessed the recording link.

Q: Does CallPage work with OpenAI Agents SDK handoffs?

It works natively. One agent can run listleads to gather new prospects, then hand off the context to a specialized evaluation agent. The tools remain available across the entire agent lifecycle.

Connect CallPage to OpenAI Agents SDK to build production sales agents that track callbacks and manage leads with built-in guardrails.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CallPage MCP to OpenAI Agents SDK

Create your Vinkius account to connect CallPage 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 CallPage with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Track callbacks with OpenAI Agents SDK

Your agent pulls real-time callback data using the `list_calls` tool. It grabs the exact recording links and call statuses straight from your account. Instead of writing custom API wrappers, your system automatically discovers these endpoints on startup. Fetching individual records happens through `get_call_details` and `get_lead_details`. The SDK validates every request before it hits the CallPage MCP server, ensuring your specialized sales agents only access the records they need.

Configure widget settings dynamically

Reading widget configurations is handled by the `get_widget_settings` and `list_widgets` tools. You can build an agent that checks if the callback prompt is active during business hours. Handoffs between agents work perfectly here—one agent checks the settings while another reviews the sales pipeline. Team structure mapping relies on `list_departments` and `list_managers`. Your system reads the exact routing rules for incoming callbacks. Tracing in the OpenAI dashboard shows exactly which department your agent queried.

Read SMS templates and account data

The `list_sms_templates` tool exposes your pre-written text messages to the agent context. This lets your production system verify which follow-up messages went out after a missed call. Everything runs through the Vinkius HTTP stream, keeping the connection stable. Core manager details come from `get_account_info`. If you need to audit which agent handles specific territories, the SDK pulls that data directly. You just pass the Vinkius URL to `MCPServerStreamableHttp` and the tools are ready.

Setup guide

Set up CallPage 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 CallPage tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate CallPage 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="CallPage Agent",
            instructions="You have access to CallPage 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 CallPage. 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 CallPage 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 CallPage MCP in OpenAI Agents SDK

Initialize `MCPServerStreamableHttp` with your Vinkius endpoint URL. Pass it to your Agent constructor using the `mcp_servers` parameter. Set `cacheToolsList=True` to speed up tool discovery on boot.

Yes, the `list_calls` tool returns the recording URLs for your callbacks. Your agent can pass these URLs to a transcription model. The SDK traces exactly when the agent accessed the recording link.

It works natively. One agent can run `list_leads` to gather new prospects, then hand off the context to a specialized evaluation agent. The tools remain available across the entire agent lifecycle.

The server reads any widget tied to your account token. Running `list_widgets` returns the full array of active callback forms. Your agent can then drill down using `get_widget_settings`.

Every request runs inside an ephemeral V8 Isolate Sandbox. When your agent queries phone numbers or lead contact details, the environment spins up instantly and destroys itself after the response. Zero data persists on our infrastructure.

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