How to Use the Lingyi Wanwu MCP in LangChain

Q: How do I connect the Lingyi Wanwu MCP server to LangChain?

Install langchain-mcp-adapters and use the MultiServerMCPClient to point to the Vinkius URL. You then call client.gettools() to pull chatcompletions and other tools directly into your agent's tool list.

Q: Can I trace Lingyi Wanwu MCP server calls with LangChain and LangSmith?

Yes, every tool call like getembeddings or chatcompletions is automatically tracked by LangSmith when you run your chain. You will see the exact inputs, outputs, and latency for each step.

Q: How do I handle rate limits for Lingyi Wanwu in LangChain?

Use getusage inside your custom chain logic to monitor your API limits before triggering heavy batches. If you hit limits, LangChain's built-in retry handlers can back off based on those metrics.

Q: Can I dynamically list available models in my chain?

The listmodels tool allows your agent to query the active Yi models at runtime. Your LangChain router can then dynamically assign the best-suited model to the next step of your chain.

Run Yi models directly inside your LangChain chains and trace every token with LangSmith.

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 LangChain

Create your Vinkius account to connect Lingyi Wanwu to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Yi chat models with LangChain agents

This MCP Server connects LangChain's ReAct agents to the `chat_completions` tool so your runs can hit Yi models without leaving your pipeline. You pass the tool list directly to your agent runner, letting the model decide when to trigger a generation step based on previous chain outputs. LangSmith tracks these calls automatically, giving you exact latency and input parameters for every single prompt. You don't have to write custom wrappers to parse the payload because the adapter maps the schemas natively.

Filter and moderate pipeline inputs

You can insert safety checks into any LangChain runnable sequence using the `check_moderation` tool. Before passing user inputs to a downstream database or vector store, the chain routes the text to this endpoint to flag policy violations immediately. This stops bad data before it hits your persistent storage or triggers expensive model calls. Because it runs as a standard step in your graph, you can branch your logic based on the moderation verdict without writing complex error-handling loops.

Track token spend across complex chains

The `get_usage` tool lets your LangChain workflows monitor their own API consumption dynamically using this MCP Server. You can build a custom step that queries current account statistics and halts execution or alerts your team if a specific chain starts burning through tokens too fast. This is critical when running autonomous loops that might otherwise run away in an infinite execution cycle. By checking real-time usage metrics directly within the graph, you keep your production costs entirely predictable.

Setup guide

Set up Lingyi Wanwu MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Lingyi Wanwu tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "lingyi-wanwu-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Lingyi Wanwu transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

Install `langchain-mcp-adapters` and use the `MultiServerMCPClient` to point to the Vinkius URL. You then call `client.get_tools()` to pull `chat_completions` and other tools directly into your agent's tool list.

Yes, every tool call like `get_embeddings` or `chat_completions` is automatically tracked by LangSmith when you run your chain. You will see the exact inputs, outputs, and latency for each step.

Use `get_usage` inside your custom chain logic to monitor your API limits before triggering heavy batches. If you hit limits, LangChain's built-in retry handlers can back off based on those metrics.

The `list_models` tool allows your agent to query the active Yi models at runtime. Your LangChain router can then dynamically assign the best-suited model to the next step of your chain.

Your raw string prompts and moderation payloads are sent directly to the Yi endpoints via an encrypted, ephemeral V8 sandbox. Vinkius never caches or stores your text inputs, ensuring your proprietary data remains completely isolated and immediately deleted post-execution.

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