iyzico

iyzico is a skill for Claude Code, Codex from seyithanalkan/iyzico-mcp. It costs 119 tokens per session (1,473 once invoked), scanned A, original, MIT.

An integration with iyzico, a payment service used in Turkey. It can inspect card details such as issuing-bank codes and instalment plans, create checkout forms, and manage payments, refunds, cancellations, and subscriptions.

In plain words
What is it for?
Creating hosted checkouts, checking instalment options, confirming payments, cancelling or refunding charges, and inspecting recurring subscriptions.
Why use it?
It lets an agent handle common Turkish payment tasks through one service while requiring confirmation before actions that move or reverse money.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Creating hosted checkouts, checking instalment options, confirming payments, cancelling or refunding charges, and inspecting recurring subscriptions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/seyithanalkan/iyzico-mcp/iyzico
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 seyithanalkan/iyzico-mcp --skill iyzico
Clone the repo
git clone --depth 1 https://github.com/seyithanalkan/iyzico-mcp

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.

agentmods badge for iyzico

README.md
[![agentmods](https://agentmods.dev/badge/skills/seyithanalkan/iyzico-mcp/iyzico/github.svg)](https://agentmods.dev/skills/seyithanalkan/iyzico-mcp/iyzico)
Your own site
<a href="https://agentmods.dev/skills/seyithanalkan/iyzico-mcp/iyzico"><img src="https://agentmods.dev/badge/skills/seyithanalkan/iyzico-mcp/iyzico/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.

agentmods 80×15 button for iyzico

Your own site · 80×15
<a href="https://agentmods.dev/skills/seyithanalkan/iyzico-mcp/iyzico"><img src="https://agentmods.dev/badge/skills/seyithanalkan/iyzico-mcp/iyzico.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 119 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,473 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00119 $0.01473
Opus 5.5 $0.00048 $0.00589
Sonnet 5.5 $0.00024 $0.00295
Haiku 4.5 $0.00012 $0.00147

Measured 20d ago against content hash 35f135122656, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

iyzico 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 20d 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.

skills/iyzico/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

iyzico

This skill tells you when and how to use the tools from the iyzico MCP server (iyzico-mcp). The server signs every request and validates inputs; your job is to pick the right tool, pass the right identifiers, and never move money without the user's say-so.

Before anything else

  1. Call ping once at the start of an iyzico task. It confirms the credentials work and reports the active environment.
  2. Tell the user which environment you are on. sandbox is the default and is safe. If it says production, every write moves real money.
  3. If ping fails with a missing variable, the user needs to set IYZICO_API_KEY and IYZICO_SECRET_KEY in their MCP client config. Do not ask them to paste keys into the chat.

Safety rules

  • Confirm every write. cancel_payment and refund_payment cannot be undone. Before calling either, state the payment, the amount, the currency and the environment, and wait for an explicit yes. In production, confirm each call separately, even within one multi-item refund.
  • Never handle card numbers. check_bin and retrieve_installment_info take only the first 6-8 digits. If the user pastes a full card number, do not repeat it or send it anywhere; use only its first 6 digits.
  • No card entry through you. Payments are taken on iyzico's hosted checkout form. You create the form; the buyer types their card there.
  • Do not fulfil an order until retrieve_checkout_form_result shows success.

Which tool for which job

Goal Tool Writes?
Check setup and environment ping no
Bank, card type, Troy/Visa/MC, domestic or not check_bin no
Taksit options and the cost of each retrieve_installment_info no
Take a payment initialize_checkout_form creates a pending session, no money moves
Did the buyer pay? retrieve_checkout_form_result no
Full detail of a payment, item transaction ids retrieve_payment no
Same-day full reversal cancel_payment yes
Full or partial refund after settlement refund_payment yes
List or filter subscriptions search_subscriptions no
One subscription's plan, status, period retrieve_subscription no

Read the full file on GitHub · 118 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.

  1. 20d ago First seen · 118 lines · 119 tokens per session scan A 35f135122656

Subscribe to this mod's changes

iyzico is a skill published in the GitHub repository seyithanalkan/iyzico-mcp (0 stars, last pushed 22d ago), licensed MIT. It adds 119 tokens to every session and 1,473 once invoked, about $0.0005 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 2026-10-19.

Related

iyzico compared with skills from other repositories

iyzico next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
iyzicoseyithanalkan/iyzico-mcpSkill022d agoMITA119Claude Code, Codex
stripegbrlpzz/prime-agent-stripe-mcpSkill22mo agoMITA79Claude Code, Codex
payment-reconciliation-automationfinsilabs/awesome-ecommerce-skillsSkill6316d agoMITA31Claude Code, Codex
stripe-integrationfinsilabs/awesome-ecommerce-skillsSkill6316d agoMITA29Claude Code, Codex
skill-stripe-integrationIAPro-Community/Orquestrador-MaestroSkill632d agoApache-2.0A37Claude Code, Codex
paypal-integrationfinsilabs/awesome-ecommerce-skillsSkill6316d agoMITB33Claude Code, Codex
recurrent-paymenttheYahia/WWmcpSkill381mo agoMITA26Claude Code