How to Use the Lingyi Wanwu MCP in LlamaIndex

Q: How do I ingest data from the Lingyi Wanwu MCP server into LlamaIndex?

Use llama-index-tools-mcp to initialize the BasicMCPClient with your Vinkius endpoint. Convert the client into tools using McpToolSpec and pass them to your FunctionAgent to access getembeddings or chatcompletions.

Q: Can I use Lingyi Wanwu embeddings to build a LlamaIndex vector index?

Yes, you can generate document vectors using the getembeddings tool. LlamaIndex then stores these vectors in your chosen database using the MCP server, allowing you to run semantic searches against them.

Q: How do I secure content before querying Lingyi Wanwu in LlamaIndex?

Run user queries through the checkmoderation tool before passing them to your LlamaIndex retriever. This guarantees that offensive or unsafe queries are caught and blocked before hitting your vector database or generating a response.

Q: Does this tool support asynchronous execution in LlamaIndex?

You can run totoollistasync() on the tool spec to load the tools asynchronously. This prevents blocking your main query loop when fetching completions or embeddings.

Index Yi model outputs into LlamaIndex vector stores to build highly accurate, live RAG applications.

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 LlamaIndex

Create your Vinkius account to connect Lingyi Wanwu to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Vectorize text for index insertion

This MCP Server exposes the `get_embeddings` tool directly to LlamaIndex's ingestion pipeline for instant vector generation. You can pass raw document chunks directly to this tool and write the resulting vectors straight into your index. Manual extraction scripts are no longer necessary. Your query engine can then use these exact same embeddings to retrieve highly relevant context during search phases.

Ground agent responses with live model checks

The `list_models` tool allows your LlamaIndex query engine to verify which Yi models are currently available before executing a generation task. Your agent can query this list to adapt its prompt structure depending on whether it is talking to a lightweight or a high-parameter model. This prevents runtime failures when models undergo updates or deprecations. By checking active models dynamically, your RAG application maintains consistent uptime.

Monitor ingestion costs and token usage

You can track indexing expenses by querying the `get_usage` tool during large-scale document parsing runs. LlamaIndex can log these metrics after each batch to ensure your vectorization process stays within budget. This gives you immediate visibility into how much data you are processing. Instead of waiting for a monthly bill, you get real-time cost tracking directly inside your pipeline logs.

Setup guide

Set up Lingyi Wanwu MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Lingyi Wanwu MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Lingyi Wanwu tools.",
)
response = await agent.run("List recent Lingyi Wanwu data")

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 LlamaIndex

Use `llama-index-tools-mcp` to initialize the `BasicMCPClient` with your Vinkius endpoint. Convert the client into tools using `McpToolSpec` and pass them to your `FunctionAgent` to access `get_embeddings` or `chat_completions`.

Yes, you can generate document vectors using the `get_embeddings` tool. LlamaIndex then stores these vectors in your chosen database using the MCP server, allowing you to run semantic searches against them.

Run user queries through the `check_moderation` tool before passing them to your LlamaIndex retriever. This guarantees that offensive or unsafe queries are caught and blocked before hitting your vector database or generating a response.

You can run `to_tool_list_async()` on the tool spec to load the tools asynchronously. This prevents blocking your main query loop when fetching completions or embeddings.

Only the raw text chunks requiring vectorization are sent to the `get_embeddings` endpoint. These payloads are processed in a secure, isolated container that instantly discards the data once the vector arrays are returned to your LlamaIndex client.

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