How to Use the ConnectAndSell MCP in OpenAI Agents SDK

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

Install the SDK with pip install openai-agents and pass the Vinkius URL into MCPServerStreamableHttp. Register this MCP Server in the mcpservers array of your Agent constructor to let the agent auto-discover the dialing tools.

Q: How does caching improve ConnectAndSell performance in OpenAI Agents SDK?

Setting cacheToolsList=True stops the SDK from repeatedly querying the Vinkius endpoint for the dialer tools. This reduces latency when your python agents frequently pull call summaries.

Q: Does this setup support real-time call tracking?

Your agent can poll listconversations at set intervals to track successful connections. It processes these records inside your Python runtime as soon as the dialer logs them.

Get raw dialer data into your OpenAI Agents SDK workflows without leaving your Python runtime.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ConnectAndSell MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run ConnectAndSell MCP Server tool calls with guardrails

The `list_call_attempts` tool exposes raw outbound dialing logs directly to your Python agents. You configure the `MCPServerStreamableHttp` client with your Vinkius endpoint, letting the SDK auto-discover these call metrics so your agent can inspect dials over specific date ranges. Because the OpenAI Agents SDK forces hard guardrails, your agent won't make blind decisions when reviewing these attempts. It inspects the dial counts, flags low-volume reps, and feeds that raw performance data straight into your tracing dashboard.

Route dialer performance to specialized agents

The `get_performance_summary` tool fetches high-level connection rates and rep activity data. Your supervisor agent calls this endpoint to pull the daily numbers, then hands off the analytical heavy lifting to a specialized reporting agent. This handoff happens natively within your Python setup using the agent's built-in routing. Setting `cacheToolsList=True` keeps these handoffs fast, preventing lag when agents swap dialer context back and forth.

Push call data to your CRM from OpenAI Agents SDK

The `sync_to_crm` tool pushes raw dial logs from your outbound campaigns straight into Salesforce or HubSpot using this MCP Server. Your post-call agent identifies completed conversations, grabs the call ID, and triggers this sync programmatically. If the sync fails or times out, the SDK's built-in validation catches the error before it corrupts your pipeline. You get full visibility into the execution path on your OpenAI developer dashboard.

Setup guide

Set up ConnectAndSell 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 ConnectAndSell tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the SDK with `pip install openai-agents` and pass the Vinkius URL into `MCPServerStreamableHttp`. Register this MCP Server in the `mcp_servers` array of your Agent constructor to let the agent auto-discover the dialing tools.

Yes, you can share the registered MCP Server across multiple specialized agents. One agent can watch lists with `list_assigned_lists` while another handles CRM syncs using `sync_to_crm`.

Setting `cacheToolsList=True` stops the SDK from repeatedly querying the Vinkius endpoint for the dialer tools. This reduces latency when your python agents frequently pull call summaries.

Your agent can poll `list_conversations` at set intervals to track successful connections. It processes these records inside your Python runtime as soon as the dialer logs them.

Your ConnectAndSell call records, user lists, and CRM tokens never touch an external database. Vinkius isolates each execution in an ephemeral sandbox, passing credentials directly to the dialer API over HTTPS.

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