How to Use the Mastercard MCP in LlamaIndex

Q: How do I index Mastercard merchant data from searchmerchants using LlamaIndex?

You'd use the McpToolSpec to get the tools and then run searchmerchants for a given area. The list of merchants returned can be converted into Document objects and loaded into any LlamaIndex vector store for querying.

Q: How does LlamaIndex handle the schemas of the 12 different Mastercard tools?

The McpToolSpec automatically converts the OpenAPI schema from the MCP server into function definitions that LlamaIndex agents can understand and use. You don't have to manually define the inputs and outputs for each tool.

Ground your financial RAG apps in a searchable index of real-time Mastercard data 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 Mastercard MCP to LlamaIndex

Create your Vinkius account to connect Mastercard 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 Mastercard with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build a Queryable Merchant Database

Don't just find merchants; index them. Set up a routine that uses `search_merchants` and `get_merchant` to pull down data for specific regions or categories. LlamaIndex then turns this raw data into a structured, searchable knowledge base. Now your users can ask questions in plain English, like "find me a 24-hour grocery store that accepts Google Pay in downtown Seattle." Your LlamaIndex query engine will find the answer from the indexed Mastercard data, not by hallucinating. It's RAG, but for real-world commerce.

Uncover Fraud Patterns with RAG

Turn raw fraud data into institutional knowledge. As you use `submit_fraud_report`, you can index the non-sensitive metadata—like fraud type, merchant category, and card type from `bin_lookup`—into a LlamaIndex vector store. This creates a searchable history of fraud incidents. A security analyst can then run complex queries like, "Show me recent counterfeit card fraud reports at gas stations involving commercial cards." LlamaIndex finds the relevant reports, giving your team a huge head start on investigations.

Your LlamaIndex MCP Server for Finance

A LlamaIndex query engine combines stored knowledge with live data. It might first check its index for information about a merchant. If the data is stale or missing, it can decide to call the `get_place_details` tool for a live update from the Mastercard network. This is the core of knowledge-augmented AI. You get the speed of querying an index with the accuracy of live API calls from this MCP server. Your application is always grounded in the most current, relevant data available.

Setup guide

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

You'd use the `McpToolSpec` to get the tools and then run `search_merchants` for a given area. The list of merchants returned can be converted into `Document` objects and loaded into any LlamaIndex vector store for querying.

Yes, that's a key feature. You configure the tools within a `FunctionAgent` or query engine. If the information isn't in the index, the agent can decide to call `get_place_details` directly to get a live answer from the Mastercard API.

Index your internal data first. Then, provide the Mastercard tools to your LlamaIndex agent. The agent can then use both your indexed internal knowledge and the live tools to answer queries, giving it complete context.

The `McpToolSpec` automatically converts the OpenAPI schema from the MCP server into function definitions that LlamaIndex agents can understand and use. You don't have to manually define the inputs and outputs for each tool.

Vinkius servers don't log the sensitive data you send. When using `bin_lookup`, you're only sending a 6-8 digit prefix, not a full card number. It's on you to decide what data from the tool's output—like issuer bank or card type—is safe to store in your LlamaIndex index.

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