How to Use the Audienceful MCP in OpenAI Agents SDK

Q: Can OpenAI Agents SDK read my Audienceful campaign reports?

Yes. The framework calls listsendreports to grab recent delivery data. Your agent can then parse those metrics and generate performance summaries.

Q: What happens if an agent tries to delete an Audienceful subscriber via MCP?

The SDK's built-in guardrails catch the deleteperson request before it fires. You configure the exact safety constraints needed for destructive actions. Execution blocks until those conditions are met.

Q: Does OpenAI Agents SDK support filtering Audienceful subscriber lists?

Calling listpeople accepts parameters for status and specific email addresses. The agent passes those arguments to narrow down the returned JSON payload.

Connect the Audienceful MCP Server to your OpenAI Agents SDK build to manage subscribers and trigger email automations from your code.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Audienceful MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Programmatic audience growth via OpenAI Agents SDK

Managing subscriber records happens instantly through the `create_person` and `update_person` tools. Your agent handles incoming leads, validates the email addresses, and pushes them directly into your Audienceful lists. Handoffs between specialized agents mean one routine can scrape contact info while another creates the actual profile. Finding existing users requires just a UID via `get_person`. If a contact opts out, the agent executes `delete_person` to wipe them from the database. Guardrails built into the framework ensure these destructive actions require explicit validation before execution.

Map dynamic data schemas

Customizing contact profiles relies on the `create_custom_field` and `list_custom_fields` tools. Agents can read your existing schema, identify missing data points for a specific campaign, and generate the required fields on the fly. This setup works perfectly when piping data from external CRM tools into your email lists. Removing outdated tags is just as straightforward using `delete_custom_field`. You maintain strict control over what gets stored because the OpenAI dashboard traces every single API call. That visibility prevents rogue agents from abusing this MCP connection.

Trigger and track email automations

Launching targeted sequences requires the `trigger_automation` tool linked to a specific subscriber profile. Your application evaluates user behavior, decides they need a drip campaign, and fires off the request. Everything happens asynchronously within your Python context manager. Measuring campaign performance uses the `list_send_reports` tool to pull recent delivery metrics. The agent pulls those numbers into its context window and summarizes open rates for your dashboard. Deploying this MCP Server gives your system read and write access to your entire email operation without writing custom integration code.

Setup guide

Set up Audienceful 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 Audienceful tools at runtime.
3

Create your Agent

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

Run the agent

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

Pass the Vinkius endpoint URL into the MCPServerStreamableHttp parameter. You then supply that configuration to your Agent constructor's server list. Set cacheToolsList to true to speed up tool discovery.

Yes. The framework calls list_send_reports to grab recent delivery data. Your agent can then parse those metrics and generate performance summaries.

The SDK's built-in guardrails catch the delete_person request before it fires. You configure the exact safety constraints needed for destructive actions. Execution blocks until those conditions are met.

Calling list_people accepts parameters for status and specific email addresses. The agent passes those arguments to narrow down the returned JSON payload.

Vinkius isolates your connection in a V8 sandbox that destroys itself after the session ends. Your agent handles sensitive PII like email addresses and UIDs through a zero-trust tunnel. No subscriber records ever touch disk outside of your own 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