How to Use the DingConnect MCP in LlamaIndex

Q: How do I index DingConnect catalog data using LlamaIndex?

Use the MCP tool spec to load listavailabletopupproducts output directly into your document pipeline. This builds a searchable index of current mobile packages that your RAG system can query.

Q: Can I run semantic queries on DingConnect transaction logs?

Yes, you can index the output of listtransactionhistory into your vector store. This lets LlamaIndex answer complex questions about your transfer history using semantic search.

Q: How do I handle real-time balance updates in a LlamaIndex application?

Do not index the output of getaccountcreditbalance because balance data changes constantly. Instead, configure your agent to call this tool directly for live checks while using indexed data for static lookups.

Q: What tools should I use to map supported countries?

Call listsupportedcountries to feed the complete country list into your index. This gives your query engine a reliable lookup source for geographic routing.

Index live mobile operator data and run RAG query pipelines over DingConnect with LlamaIndex.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DingConnect MCP to LlamaIndex

Create your Vinkius account to connect DingConnect 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 DingConnect with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Indexing local operator data into LlamaIndex

`list_mobile_operators` pulls raw provider directories directly into your LlamaIndex document store. Your RAG pipeline searches this indexed data to match user queries with local carrier profiles instantly. This approach bypasses repeated live API calls by letting you query the vector store for static country details. You get faster response times while keeping your local knowledge base fresh with actual network configurations.

Semantic search over DingConnect product catalogs

`search_topup_products` feeds live catalog data into your LlamaIndex indexers for semantic retrieval. Users can search for packages using natural language, and your agent matches their intent against the indexed product list. Combining this tool with `list_available_topup_products` ensures your index stays updated with current SKUs. Your agent queries this local index first to prevent hallucinated pricing or unavailable data packages.

Auditing transaction histories using this MCP Server

`list_transaction_history` outputs your recent top-up records so LlamaIndex can index them for automated financial reporting. Your agent queries this index to find spending trends and spot failed transactions without manual exports. This MCP Server connection lets you run natural language questions over your raw transactional history. You can ask your agent which regions had the highest volume, and it will resolve the query by reading the indexed logs.

Setup guide

Set up DingConnect 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 DingConnect 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 DingConnect tools.",
)
response = await agent.run("List recent DingConnect 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 DingConnect. 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 DingConnect 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 DingConnect MCP in LlamaIndex

Use the MCP tool spec to load `list_available_topup_products` output directly into your document pipeline. This builds a searchable index of current mobile packages that your RAG system can query.

Yes, you can index the output of `list_transaction_history` into your vector store. This lets LlamaIndex answer complex questions about your transfer history using semantic search.

Do not index the output of `get_account_credit_balance` because balance data changes constantly. Instead, configure your agent to call this tool directly for live checks while using indexed data for static lookups.

Call `list_supported_countries` to feed the complete country list into your index. This gives your query engine a reliable lookup source for geographic routing.

The server handles your transaction logs and API metadata inside an ephemeral sandbox on Vinkius. These data points are only pulled during active tool execution and are never cached or stored on external servers.

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