Mastercard MCP Server for OpenAI Agents SDK 12 tools — connect in under 2 minutes
The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Mastercard through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp
async def main():
# Your Vinkius token. get it at cloud.vinkius.com
async with MCPServerStreamableHttp(
url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
) as mcp_server:
agent = Agent(
name="Mastercard Assistant",
instructions=(
"You help users interact with Mastercard. "
"You have access to 12 tools."
),
mcp_servers=[mcp_server],
)
result = await Runner.run(
agent, "List all available tools from Mastercard"
)
print(result.final_output)
asyncio.run(main())
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
About Mastercard MCP Server
Connect Mastercard payment infrastructure to any AI agent and unlock powerful payment intelligence, fraud detection, merchant discovery, and card validation capabilities through natural conversation.
The OpenAI Agents SDK auto-discovers all 12 tools from Mastercard through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Mastercard, another analyzes results, and a third generates reports, all orchestrated through Vinkius.
What you can do
- BIN Lookup — Identify any payment card's issuer bank, card type (credit/debit/prepaid/commercial), category (Standard/Gold/Platinum/World/World Elite), issuing country, and special flags from just the first 6-8 digits
- Account Validation — Verify if a payment card number is active and valid before processing transactions, reducing declined payments and fraud risk
- Merchant Search — Find Mastercard-accepting merchants near any GPS coordinates, filterable by business category (MCC codes)
- Places Discovery — Discover nearby payment-accepting locations with digital wallet support (Apple Pay, Google Pay, contactless)
- Address-Based Search — Search for merchants by street address instead of coordinates for user-friendly location queries
- Merchant Details — Retrieve complete information about specific merchants including addresses, MCC codes, and accepted payment methods
- MCC Code Reference — Access the complete Merchant Category Code database to understand business classifications
- Fraud Reporting — Submit confirmed fraudulent transactions to Mastercard's Fraud and Loss Database to protect the network
- Nearby Locations — Discover ATMs, merchants, and points of interest around any geographic location
The Mastercard MCP Server exposes 12 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.
How to Connect Mastercard to OpenAI Agents SDK via MCP
Follow these steps to integrate the Mastercard MCP Server with OpenAI Agents SDK.
Install the SDK
Run pip install openai-agents in your Python environment
Replace the token
Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com
Run the script
Save the code above and run it: python agent.py
Explore tools
The agent will automatically discover 12 tools from Mastercard
Why Use OpenAI Agents SDK with the Mastercard MCP Server
OpenAI Agents SDK provides unique advantages when paired with Mastercard through the Model Context Protocol.
Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety
Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure
Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate
First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output
Mastercard + OpenAI Agents SDK Use Cases
Practical scenarios where OpenAI Agents SDK combined with the Mastercard MCP Server delivers measurable value.
Automated workflows: build agents that query Mastercard, process the data, and trigger follow-up actions autonomously
Multi-agent orchestration: create specialist agents. one queries Mastercard, another analyzes results, a third generates reports
Data enrichment pipelines: stream data through Mastercard tools and transform it with OpenAI models in a single async loop
Customer support bots: agents query Mastercard to resolve tickets, look up records, and update statuses without human intervention
Mastercard MCP Tools for OpenAI Agents SDK (12)
These 12 tools become available when you connect Mastercard to OpenAI Agents SDK via MCP:
bin_lookup
Returns comprehensive card information including: issuer bank name, card type (credit/debit/prepaid/commercial), card category (Standard/Gold/Platinum/World/World Elite), issuing country, currency, and special flags (healthcare, payroll, purchasing). Use this to identify unknown cards, validate card ranges before transactions, determine cross-border fees, or understand the cardholder profile. The accountNumberPrefix parameter must be 6-8 numeric digits. Optional parameters (currencyCode, paymentType, merchantCategoryCode) provide more precise results for specific transaction contexts. Identify card issuer, type, and details from the first 6-8 digits of a payment card number
bin_lookup_post
Returns identical card identification data: issuer bank, card type, category, country, and product flags. Use this method when handling sensitive payment data in compliance-focused applications. The accountNumberPrefix should be 6-8 digits. Optional context parameters (currency, payment type, MCC) refine results. Identify card issuer using POST method for enhanced security with sensitive card data
get_merchant
Returns full address, contact information, MCC code, operating hours, and accepted payment methods. Use this to get in-depth information about a specific merchant location after finding it via search. The merchant ID is a unique identifier returned by the search_merchants tool. Get detailed information about a specific Mastercard-accepting merchant
get_place_details
Returns full address, coordinates, MCC code, payment methods accepted, operating hours, and other merchant attributes. Use this after a places search to drill down into a specific location. The locationId is returned by search_places or search_places_by_address tools. Get complete details for a specific merchant place by its location ID
merchant_category_codes
MCC codes are 4-digit numbers that classify businesses by type (e.g., 5411 = Grocery Stores, 5812 = Restaurants, 4511 = Airlines). Use this to understand merchant classifications, filter searches by business type, or decode MCC values found in transaction data. Optional limit parameter controls how many codes to return. List all Merchant Category Codes (MCC) used to classify business types
merchant_industry_codes
Industry codes group related MCC codes into higher-level categories. Use this to understand the hierarchical classification of merchants, analyze industry-level spending patterns, or build category navigation interfaces. List all merchant industry codes for broader business classification
nearby_locations
Returns names, addresses, categories, and distances from the search point. Use this for "what is nearby" queries, travel planning, or finding payment infrastructure in an area. Latitude and longitude are required. Radius in meters defines the search area. Limit controls maximum results returned. Discover points of interest and payment locations near GPS coordinates
search_merchants
Returns merchant names, addresses, MCC codes, and precise coordinates. Use this to find nearby payment-accepting locations, analyze merchant density in an area, or build "find merchants near me" features. Latitude and longitude are required as strings (e.g., "-23.5505", "-46.6333"). Radius is in meters (e.g., 5000 for 5km). Optionally filter by MCC category code (e.g., "5411" for grocery stores, "5812" for restaurants). Limit controls result count (max 50). Find Mastercard-accepting merchants near specific GPS coordinates filtered by category
search_places
Returns detailed merchant information including whether they accept Apple Pay, Google Pay, contactless payments, and their MCC classification. Use this when users need to find payment-accepting locations with specific digital wallet support. Latitude and longitude are required as numbers. Distance is in kilometers. Optionally filter by country code (ISO 3166-1 alpha-2) and payment capabilities (hasApplePay, hasGooglePay). Search for merchant places using GPS coordinates with payment method filters
search_places_by_address
The API geocodes the address internally. Returns nearby merchants with payment capability details (Apple Pay, Google Pay, contactless). Use this when users provide an address rather than GPS coordinates. Required: address line 1, city, country code, and postal code. Optional: state/province code (countrySubdivisionCode) for more precise results. Example: addressLine1="1600 Amphitheatre Pkwy", city="Mountain View", countryCode="US", postalCode="94043". Search for merchant places using a street address instead of coordinates
submit_fraud_report
This is a critical tool for issuers and processors to flag fraudulent transactions in real-time. Required fields: accountNumber (card number), transactionAmount, transactionCurrency (ISO 4217), and fraudTypeCode. Fraud type codes: "01" = Stolen Card Fraud, "02" = Never Received Card, "03" = Fraudulent Application, "04" = Counterfeit Card Fraud. Optional: fraudAmount (if different from transaction amount), transactionDate (YYYY-MM-DD). Use this only for confirmed fraud cases — never for suspected or disputed transactions. This helps Mastercard improve fraud detection and reduce false positives across the network. IMPORTANT: This action should only be performed by authorized fraud management personnel. Report a confirmed fraudulent transaction to Mastercard Fraud and Loss Database
validate_account
Returns validation status (VALID/INVALID), account type, and issuer information. Use this to verify card validity before processing transactions, reduce declined transactions, or perform account verification during onboarding. Required: accountNumber (full card number). Optional: expiryDate (MMYY format), cardholderName for enhanced validation. Handle card numbers securely — never log or store full PANs. Validate a payment card account number to check if it is active and valid
Example Prompts for Mastercard in OpenAI Agents SDK
Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Mastercard immediately.
"What type of card is 542418 and which bank issued it?"
"Find restaurants near São Paulo city center that accept Mastercard within 3km."
"Validate card number 5123456789012346 before I process this payment."
Troubleshooting Mastercard MCP Server with OpenAI Agents SDK
Common issues when connecting Mastercard to OpenAI Agents SDK through the Vinkius, and how to resolve them.
MCPServerStreamableHttp not found
pip install --upgrade openai-agentsAgent not calling tools
Mastercard + OpenAI Agents SDK FAQ
Common questions about integrating Mastercard MCP Server with OpenAI Agents SDK.
How does the OpenAI Agents SDK connect to MCP?
MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.Can I use multiple MCP servers in one agent?
MCPServerSse instances to the agent constructor. The agent can use tools from all connected servers within a single run.Does the SDK support streaming responses?
Connect Mastercard with your favorite client
Step-by-step setup guides for every MCP-compatible client and framework:
Anthropic's native desktop app for Claude with built-in MCP support.
AI-first code editor with integrated LLM-powered coding assistance.
GitHub Copilot in VS Code with Agent mode and MCP support.
Purpose-built IDE for agentic AI coding workflows.
Autonomous AI coding agent that runs inside VS Code.
Anthropic's agentic CLI for terminal-first development.
Python SDK for building production-grade OpenAI agent workflows.
Google's framework for building production AI agents.
Type-safe agent development for Python with first-class MCP support.
TypeScript toolkit for building AI-powered web applications.
TypeScript-native agent framework for modern web stacks.
Python framework for orchestrating collaborative AI agent crews.
Leading Python framework for composable LLM applications.
Data-aware AI agent framework for structured and unstructured sources.
Microsoft's framework for multi-agent collaborative conversations.
Connect Mastercard to OpenAI Agents SDK
Get your token, paste the configuration, and start using 12 tools in under 2 minutes. No API key management needed.