How to Use the Moneypenny MCP in OpenAI Agents SDK

Q: How does the Moneypenny MCP Server handle authentication in OpenAI Agents SDK?

You pass your endpoint token during initialization using MCPServerStreamableHttp. The SDK handles the connection securely, ensuring your agents can run checkmoneypennystatus without hardcoding API keys in your prompt logic.

Q: How do I handle latency when OpenAI Agents SDK calls Moneypenny?

Set cacheToolsList=True during your setup to skip redundant tool discovery requests. This keeps your agents fast when they fetch real-time updates via gettodaychats.

Q: What happens if the Moneypenny API goes down?

Your agent can run checkmoneypennystatus to verify the connection before attempting to fetch logs. If the API is unreachable, the SDK raises a clear exception so your system can fail gracefully.

Q: How does this MCP Server protect my customer call and chat logs?

All call messages and live chat transcripts pulled via listcallmessages run through Vinkius's zero-trust sandboxed environment. Your data is processed in ephemeral memory and never stored on the platform, keeping customer communications compliant.

Feed live receptionist data directly into your OpenAI Agents SDK pipelines to handle customer calls and chats without writing custom APIs.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Moneypenny MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time receptionist monitoring

Your OpenAI Agents SDK agents can instantly monitor incoming customer calls using `get_today_calls` to see who dialed in via this MCP connection. This lets your system flag high-priority accounts and coordinate immediate follow-up tasks before the customer even hangs up. Instead of waiting for manual end-of-day reports, you configure the agent to run `get_activity_summary` at set intervals. This keeps your production pipelines updated with fresh metrics on agent performance and call volume.

Automated live chat follow-ups

When a customer finishes a chat with a live receptionist, your OpenAI Agents SDK agent uses `get_recent_chats` to pull the raw transcript immediately. This triggers custom workflows, like sending personalized follow-up emails based on the actual conversation. If the agent needs to analyze historical interactions, it invokes `list_chat_logs` to scan past conversations. You get clean, structured chat data fed directly into your agent's context window.

Safe historical call analysis with MCP Server

This MCP Server lets your OpenAI Agents SDK handle monthly audits securely by calling `get_this_month_calls` without exposing raw database credentials. Built-in guardrails validate every query before execution, preventing your agents from making unauthorized calls. You can also pull weekly trends with `get_this_week_calls` to analyze peak call times. The OpenAI dashboard traces these tool calls, making it easy to debug latency or trace data flow during heavy traffic.

Setup guide

Set up Moneypenny 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 Moneypenny tools at runtime.
3

Create your Agent

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

Run the agent

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

You pass your endpoint token during initialization using `MCPServerStreamableHttp`. The SDK handles the connection securely, ensuring your agents can run `check_moneypenny_status` without hardcoding API keys in your prompt logic.

Yes, you control this at the agent constructor level. By managing the tool list passed to your agent, you prevent it from executing tools like `list_chat_logs` while still letting it fetch today's summary.

Set `cacheToolsList=True` during your setup to skip redundant tool discovery requests. This keeps your agents fast when they fetch real-time updates via `get_today_chats`.

Your agent can run `check_moneypenny_status` to verify the connection before attempting to fetch logs. If the API is unreachable, the SDK raises a clear exception so your system can fail gracefully.

All call messages and live chat transcripts pulled via `list_call_messages` run through Vinkius's zero-trust sandboxed environment. Your data is processed in ephemeral memory and never stored on the platform, keeping customer communications 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