How to Use the Callpicker MCP in OpenAI Agents SDK

Q: How do I connect Callpicker to my OpenAI Agents SDK project?

First, pip install openai-agents, then instantiate MCPServerStreamableHttp with your Vinkius URL. Pass that server instance into the mcpservers list when you create your agent. The tools are discovered automatically.

Q: Can my OpenAI agent make phone calls using Callpicker?

Yes, the makecall tool lets your agent initiate outbound calls. The OpenAI Agents SDK has built-in guardrails, so you can require human confirmation before the call is actually placed.

Q: What kind of reports can I generate with Callpicker and the OpenAI Agents SDK?

You can pull raw data for analytics with getcdrreport or get a simple list of recent calls with listcalllogs. Your agent can then process this data or pass it to another system.

Build production agents with the OpenAI Agents SDK that manage call logs, recordings, and PBX status automatically.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Callpicker MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Call Management

Give your agent the tools to handle day-to-day phone tasks. It can initiate calls with `make_call`, check recent activity with `list_call_logs`, and pull specifics on any conversation using `get_call_details`. Because this is the OpenAI Agents SDK, you get built-in guardrails to review and approve sensitive actions before they run. This isn't for prototypes. You're building a system that works without constant supervision. Specialized agents can even hand off tasks—one agent could identify a high-priority caller from the logs, then pass the details to another agent responsible for follow-up calls. It all gets traced in your OpenAI dashboard.

Generate Reports, Find Recordings

Your agent can pull complete Call Detail Records with `get_cdr_report` for deep analysis. Or, it can just list recent conversations with `list_call_recordings` and fetch a specific download link using `get_recording_url`. No more digging through a clunky web UI to find the recording you need. Connect this to your internal workflows. An agent could be tasked to find all recordings related to a specific support ticket, download them, and summarize the findings. With full tracing in the OpenAI dashboard, you see exactly what the agent did, which tools it used, and why.

Manage Your PBX with an OpenAI Agent

Turn PBX administration into a conversation. Your agent can check the health of your phone system with `get_pbx_system_status` or get a full list of configured lines using `list_pbx_extensions`. It's a simple way to query system state without logging into another admin panel. This is where agent handoffs really shine. A monitoring agent could use `get_pbx_system_status` to detect a problem, then hand off to a remediation agent that notifies an on-call engineer and provides a list of available `list_virtual_numbers` to reroute calls. This MCP Server gives your agents the senses to monitor your phone system.

Setup guide

Set up Callpicker 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 Callpicker tools at runtime.
3

Create your Agent

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

Run the agent

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

First, `pip install openai-agents`, then instantiate `MCPServerStreamableHttp` with your Vinkius URL. Pass that server instance into the `mcp_servers` list when you create your agent. The tools are discovered automatically.

Yes, the `make_call` tool lets your agent initiate outbound calls. The OpenAI Agents SDK has built-in guardrails, so you can require human confirmation before the call is actually placed.

It uses auto-discovery. Once you connect the Callpicker MCP server, all nine tools are immediately available to your agent. Set `cacheToolsList=True` for better performance on subsequent runs.

You can pull raw data for analytics with `get_cdr_report` or get a simple list of recent calls with `list_call_logs`. Your agent can then process this data or pass it to another system.

Yes. Vinkius processes each request in a private, ephemeral sandbox. The server only handles call metadata, logs, and recording URLs—it never has access to the raw audio, which stays on your systems.

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