How to Use the Lingyi Wanwu MCP in OpenAI Agents SDK

Q: How do I register the Lingyi Wanwu MCP tools inside the OpenAI Agents SDK?

Install openai-agents and initialize the server streamable HTTP class with your Vinkius URL. Pass this instance directly into your Agent constructor using the mcpservers argument, and the SDK will auto-discover the tools.

Q: Can I use Lingyi Wanwu embeddings with OpenAI Agents SDK retrieval?

Yes. You call getembeddings through the MCP Server to generate vectors that match the Yi model semantic space. This lets your agent perform vector searches on external databases before feeding the context to the model.

Q: Does the Lingyi Wanwu integration support OpenAI Agents SDK guardrails?

Absolutely. You can wire checkmoderation directly into your agent's pre-execution hook. This ensures every prompt gets analyzed for policy violations before the agent triggers any downstream tools.

Q: How does the SDK handle tool list caching for these models?

Set cacheToolsList=True in your connection parameters. This prevents the SDK from querying the Vinkius endpoint on every single turn, reducing latency when calling chatcompletions.

Run Yi models inside your OpenAI Agents SDK pipelines with auto-discovered tools and built-in safety guardrails.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Lingyi Wanwu MCP to OpenAI Agents SDK

Create your Vinkius account to connect Lingyi Wanwu 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 Lingyi Wanwu with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Yi models inside OpenAI Agent pipelines

`chat_completions` lets you route natural language tasks directly to Yi models while maintaining OpenAI Agents SDK routing structures. Look, this MCP Server removes the headache of writing custom wrappers to translate payloads between your agent and the Chinese-language LLM endpoints. The integration handles raw text processing under the hood. It exposes `list_models` so your orchestrator actually knows which Yi model variant is active and ready to process incoming agent requests.

Enforce content safety at the agent boundary

`check_moderation` acts as an inline safety gate before your OpenAI Agents SDK agent executes any external tool calls through this MCP connection. You pass the user input through this tool to flag Chinese content policy violations before spinning up expensive Yi model runs. This setup prevents toxic or out-of-bounds prompts from hijacking your agent loop. By catching violations early, you protect your system from prompt injection attempts and save API budget on bad inputs.

Track token consumption and vector generation

`get_usage` gives your OpenAI Agents SDK supervisor agent real-time visibility into your active token spend. Instead of waiting for billing cycles, the agent queries this tool to monitor usage metrics and dynamically adjust routing behavior if limits are approaching. For retrieval tasks, `get_embeddings` generates vector representations of your data directly inside the agent context. This ensures your OpenAI Agents SDK knowledge base stays aligned with the native 384-dimensional representation space of the Yi models.

Setup guide

Set up Lingyi Wanwu 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 Lingyi Wanwu tools at runtime.
3

Create your Agent

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

Run the agent

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

Install `openai-agents` and initialize the server streamable HTTP class with your Vinkius URL. Pass this instance directly into your Agent constructor using the `mcp_servers` argument, and the SDK will auto-discover the tools.

Yes. You call `get_embeddings` through the MCP Server to generate vectors that match the Yi model semantic space. This lets your agent perform vector searches on external databases before feeding the context to the model.

Absolutely. You can wire `check_moderation` directly into your agent's pre-execution hook. This ensures every prompt gets analyzed for policy violations before the agent triggers any downstream tools.

Set `cacheToolsList=True` in your connection parameters. This prevents the SDK from querying the Vinkius endpoint on every single turn, reducing latency when calling `chat_completions`.

Vinkius processes your prompt and completion payloads inside ephemeral V8 isolates. The server never writes your raw text to persistent storage, ensuring your data is immediately discarded after the API returns the response.

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