How to Use the GeTui / 个推 MCP in OpenAI Agents SDK

Q: Can the OpenAI Agents SDK read GeTui / 个推 delivery reports?

Yes, the agent can call getpushstatus to check specific task IDs. It parses the JSON response to determine if the push succeeded or failed.

Q: What happens if an agent tries to broadcast to all users?

The agent will attempt to call pushtoall. You should configure OpenAI Agents SDK guardrails to require human approval before this specific tool executes.

Build production notification agents with OpenAI Agents SDK that manage GeTui campaigns and track delivery.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect GeTui / 个推 MCP to OpenAI Agents SDK

Create your Vinkius account to connect GeTui / 个推 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 GeTui / 个推 with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Trigger targeted pushes via MCP Server

The GeTui MCP Server lets your agent execute live notification campaigns directly from code. When your OpenAI agent decides a user needs an alert, it calls `push_to_single` to fire off the message immediately. For batch operations, the agent handles the array construction and triggers `push_to_list` to hit multiple targets at once. You don't want agents hallucinating broadcast commands. OpenAI Agents SDK guardrails ensure the agent validates the payload before it ever touches `push_to_all`. If a handoff occurs between a marketing agent and a transactional agent, the tracing dashboard logs exactly which tool fired the push.

Map internal users to devices

Mapping your internal database IDs to GeTui client IDs happens through `bind_user_alias`. Your agent takes the user identifier and links it to the device token without requiring a separate backend service. If you need to verify a connection before sending a critical alert, the agent runs `query_user_alias` to confirm the mapping exists. This eliminates blind sends. The SDK intercepts the tool call, executes the HTTP request via the MCP connection, and returns the binding status to the agent. You get a clean confirmation loop before any push logic executes.

Pull delivery stats into OpenAI Agents SDK

You can check if a device is actually online before attempting delivery using `get_cid_status`. If the user is offline, the agent can queue the message or switch to an SMS fallback. To understand campaign performance, the agent pulls `get_daily_push_report` to ingest raw delivery metrics. Broad application metrics come through `get_app_user_stats`. Your analytics agent reads these numbers, formats them, and passes them to a reporting agent for daily summaries. The entire flow runs autonomously through the configured endpoints.

Setup guide

Set up GeTui / 个推 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 GeTui / 个推 tools at runtime.
3

Create your Agent

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

Run the agent

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

Instantiate MCPServerStreamableHttp with your Vinkius endpoint. Pass it to the Agent constructor in the mcp_servers array. Tools discover automatically when you set cacheToolsList=True.

Yes, the agent can call get_push_status to check specific task IDs. It parses the JSON response to determine if the push succeeded or failed.

The agent will attempt to call push_to_all. You should configure OpenAI Agents SDK guardrails to require human approval before this specific tool executes.

You can assign specific tools to different agents. A marketing agent gets the batch push tools, while a support agent only gets access to get_cid_status to troubleshoot device connectivity.

The server only processes client IDs, aliases, and push payloads. Vinkius runs the connection in an ephemeral V8 isolate sandbox, meaning your device tokens disappear from memory the moment the HTTP request resolves.

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