What is mastercard-best-practices?

Integration guidance for Mastercard APIs, which are web services used by software to exchange payment-related data. It explains how to find a service, confirm its authentication method, select an operation, and use the correct request, response, and environment details.

Use it to look up Mastercard API documentation, choose sandbox or production URLs, and build authenticated API requests.

It reduces errors from using the wrong service identifier, authentication method, endpoint, or request format.

mastercard-best-practices — Skill by Mastercard

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add Mastercard/developers-agent-toolkit --skill mastercard-best-practices

Clone the repo

git clone --depth 1 https://github.com/Mastercard/developers-agent-toolkit

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/mastercard/developers-agent-toolkit/mastercard-best-practices/github.svg)](https://agentmods.dev/skills/mastercard/developers-agent-toolkit/mastercard-best-practices)

Your own site

<a href="https://agentmods.dev/skills/mastercard/developers-agent-toolkit/mastercard-best-practices"><img src="https://agentmods.dev/badge/skills/mastercard/developers-agent-toolkit/mastercard-best-practices/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/mastercard/developers-agent-toolkit/mastercard-best-practices"><img src="https://agentmods.dev/badge/skills/mastercard/developers-agent-toolkit/mastercard-best-practices.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 148 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,320 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00148	$0.02320
Opus 5.5	$0.00059	$0.00928
Sonnet 5.5	$0.00030	$0.00464
Haiku 4.5	$0.00015	$0.00232

Measured 15d ago against content hash c478a0d83880, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mastercard-best-practices scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 15d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

providers/agent-plugins/plugin/skills/mastercard-best-practices/SKILL.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mastercard APIs Integration Guide

Source of truth

The Mastercard Developers MCP server (@mastercard/developers-mcp, hosted at https://developer.mcp.mastercard.com) is authoritative for which services exist, what an endpoint accepts, and what the integration guides say. Call it rather than answering from memory.

get-documentation also returns the service's api_specification(s) paths, which supply the required argument for both operation tools.

If the MCP server is unavailable, the same facts are public: the service index, the authentication guides, and each service's https://developer.mastercard.com/{serviceId}/documentation/llms-full.txt, which carries auth_type in its frontmatter. These are a fallback, not a substitute.

Start with the index: resolve the service, then read its auth type

Service names as marketed differ from the serviceId used to address them. The index maps one to the other and carries the auth type.

Server connected: call get-services-list. Its response contains Products and Services; only Services carry a serviceId, which is what every other tool takes.
Server unavailable: the index is published at https://developer.mastercard.com/llms.txt.

Both give the same entry per service:

### <Service Name>
serviceId: <service-id>
authType: <auth type>
sourceUrl: https://developer.mastercard.com/<service-id>/documentation/index.md

If more than one service matches the name, list the candidates and ask which one including the description of the service. "The Locations API" matches three distinct services: locations (ATM Locations), locations-intelligence (Locations) and locations-merchants (Location Services).

Never construct a serviceId from the service name. Slugs add suffixes, drop vendor prefixes, abbreviate, differ by singular against plural, or use a different word altogether.

If the service is not in the index, stop and ask. It may be retired, renamed, or not a Mastercard Developers service.

Read the full file on GitHub · 130 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

15d ago First seen · 130 lines · 148 tokens per session scan A c478a0d83880

Subscribe to this mod's changes

mastercard-best-practices is a skill published in the GitHub repository Mastercard/developers-agent-toolkit (55 stars, last pushed 15d ago), licensed MIT. It adds 148 tokens to every session and 2,320 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-01.

Backend and APIs Finance and fintech LLM api chatgpt developers generative-ai mcp

api-design-expert

Expert-level API design principles, REST, GraphQL, versioning, and API best practices. Use when the user mentions REST, GraphQL, API versioning, or API security, or when the task involves API Design Principles, API Styles, or Documentation.

personamanagmentlayer/pcl · 57 tokens

microservices-expert

Expert-level microservices architecture, patterns, service mesh, and distributed systems. Use when the user mentions distributed systems, service mesh, or architecture, or when the task involves Microservices Principles, Architecture Patterns, Communication, or Data Management.

personamanagmentlayer/pcl · 52 tokens

grpc-expert

Expert-level gRPC, Protocol Buffers, microservices communication, and streaming. Use when the user mentions Protocol Buffers, microservices, RPC, or streaming, or when the task involves gRPC Fundamentals, Communication Patterns, or Production Features.

personamanagmentlayer/pcl · 53 tokens

mastercard-best-practices