How to Use the Juhe Data / 聚合数据 MCP in LlamaIndex

Q: How do I index Juhe Data / 聚合数据 outputs into LlamaIndex?

You use the McpToolSpec to convert the MCP tools into LlamaIndex-compatible tools. When your agent invokes getoilprice, the output is treated as a document node that you can write directly to your vector store.

Q: Can I restrict which Juhe Data / 聚合数据 tools LlamaIndex can access?

Yes, you can use the allowedtools filter when initializing the client. This lets you expose only specific endpoints, like getweather or getcalendarmonth, while keeping administrative tools hidden from the agent.

Q: Does Juhe Data / 聚合数据 support async queries in LlamaIndex?

Yes, you can load the tools asynchronously using totoollistasync(). This prevents your indexing pipeline from blocking when fetching large datasets like driving test questions via getdrivingtestquestions.

Q: Can I use the constellation tool for personalized content?

The getconstellationhoroscope tool provides daily horoscope data that you can index for user profiles. Your LlamaIndex agent can query these indexed horoscopes to generate personalized recommendations or localized app content.

Index live Chinese weather, financial rates, and news directly into LlamaIndex vector stores using this MCP server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Juhe Data / 聚合数据 MCP to LlamaIndex

Create your Vinkius account to connect Juhe Data / 聚合数据 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 Juhe Data / 聚合数据 with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index live Chinese market data into LlamaIndex vector stores

The `get_exchange_rate` tool feeds current currency market rates directly into your LlamaIndex data ingestion pipeline. Instead of relying on static documents, your RAG system queries this live API to update its vector index with real-time financial data. This setup prevents your agent from serving stale conversion rates to users. When a query hits your index, LlamaIndex pulls the latest numbers from the tool, indexes them, and synthesizes an accurate, grounded response.

Ground user profiles with verified identity metadata

The `get_id_card_info` tool extracts geographic and demographic metadata from Chinese ID numbers. Your pipeline indexes this structured data, allowing you to perform semantic searches over user profiles while keeping the core identity records verified. By cross-referencing this identity data with network locations using `get_ip_lookup`, you build a secure, queryable history of user sessions. LlamaIndex search agents can then query these logs to detect fraudulent patterns instantly.

Feed local news and weather into your knowledge base

The `get_latest_news` tool retrieves current headlines across China to keep your local knowledge base fresh. Your LlamaIndex agent indexes these stories as they break, ensuring your search results reflect today's news rather than outdated training data. To add seasonal context, pair the news feed with `get_weather` and `get_calendar_day` data. This gives your query engine a complete, real-time snapshot of local conditions, holidays, and events for any region in China.

Setup guide

Set up Juhe Data / 聚合数据 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 Juhe Data / 聚合数据 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 Juhe Data / 聚合数据 tools.",
)
response = await agent.run("List recent Juhe Data / 聚合数据 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 Juhe Data / 聚合数据. 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 Juhe Data / 聚合数据 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 Juhe Data / 聚合数据 MCP in LlamaIndex

You use the `McpToolSpec` to convert the MCP tools into LlamaIndex-compatible tools. When your agent invokes `get_oil_price`, the output is treated as a document node that you can write directly to your vector store.

Yes, you can use the `allowed_tools` filter when initializing the client. This lets you expose only specific endpoints, like `get_weather` or `get_calendar_month`, while keeping administrative tools hidden from the agent.

Yes, you can load the tools asynchronously using `to_tool_list_async()`. This prevents your indexing pipeline from blocking when fetching large datasets like driving test questions via `get_driving_test_questions`.

The `get_constellation_horoscope` tool provides daily horoscope data that you can index for user profiles. Your LlamaIndex agent can query these indexed horoscopes to generate personalized recommendations or localized app content.

Yes, because Vinkius runs the MCP server in a secure V8 Isolate Sandbox. Your ID queries processed by `get_id_card_info` are ephemeral, meaning the sensitive digits are never cached or written to disk during the API call.

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