How to Use the WeChat Mini-Programs / 微信小程序 MCP in OpenAI Agents SDK

Q: How do I get basic session data with WeChat Mini-Programs / 微信小程序 using OpenAI Agents SDK?

You use the codetosession tool. You pass the authorization code, and it returns a usable session token for subsequent calls. This establishes your connection to the mini-app ecosystem.

Q: Can I check if user content is safe when building WeChat Mini-Programs / 微信小程序 with OpenAI Agents SDK?

Absolutely. You use imagesecuritycheck for images and messagesecuritycheck for text. These tools give you a definitive pass/fail on sensitive material before your agent continues.

Q: If I run into data issues, what specific data type does this MCP Server touch?

This server primarily touches Account Info (via getaccountstatus), Phone Numbers (getphonenumber), and Messaging Content (for security checks and sending updates).

Connect WeChat Mini-Programs / 微信小程序 data directly to your OpenAI Agents SDK for production deployment.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect WeChat Mini-Programs / 微信小程序 MCP to OpenAI Agents SDK

Create your Vinkius account to connect WeChat Mini-Programs / 微信小程序 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 WeChat Mini-Programs / 微信小程序 with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate content before sending

Need to check images or text? These tools run security checks against sensitive material. You can pass an image through `image_security_check` or send a message snippet via `message_security_check`. The agent gets a clean pass/fail flag back, so you don't hit any compliance walls. This is critical before sending out anything official. If the content fails either check, your workflow stops right there. You keep users safe and stay compliant without needing an extra microservice layer.

Track user activity & metrics

Know how people are using the mini-app? Get visitor data with tools like `get_visit_page_trend` and `get_daily_summary`. This gives you a solid metric on engagement, showing exactly which pages users spend time on. It's better than just guessing. Plus, you can track how connected an account is using `get_account_status`. These metrics let your agent build smarter user profiles—it’s not just about the data; it's about what that data means for retention.

Manage accounts and messages

You can automate core actions, too. Use `code_to_session` to exchange an authorization code for a live session token. From there, your agent can grab the user's phone number via `get_phone_number` or send targeted updates using `send_subscribe_message`. It’s straightforward messaging. This lets your AI client handle everything from onboarding flows to follow-up campaigns without manual steps. The whole sequence runs through the MCP Server, keeping it clean and traceable.

Setup guide

Set up WeChat Mini-Programs / 微信小程序 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 WeChat Mini-Programs / 微信小程序 tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives WeChat Mini-Programs / 微信小程序 tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate WeChat Mini-Programs / 微信小程序 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="WeChat Mini-Programs / 微信小程序 Agent",
            instructions="You have access to WeChat Mini-Programs / 微信小程序 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 WeChat Mini-Programs / 微信小程序. 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 WeChat Mini-Programs / 微信小程序 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 WeChat Mini-Programs / 微信小程序 MCP in OpenAI Agents SDK

You use the `code_to_session` tool. You pass the authorization code, and it returns a usable session token for subsequent calls. This establishes your connection to the mini-app ecosystem.

Absolutely. You use `image_security_check` for images and `message_security_check` for text. These tools give you a definitive pass/fail on sensitive material before your agent continues.

Yeah, it does. Because agents auto-discover all the available MCP tools—like `get_phone_number` or `send_subscribe_message`—you just point your agent at the server and let it figure out what to do.

You're getting a ton of stuff: visit page trends, daily summaries, user phone numbers, and account status. Anything that matters for understanding the user journey is available.

This server primarily touches Account Info (via `get_account_status`), Phone Numbers (`get_phone_number`), and Messaging Content (for security checks and sending updates).

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