MCP.Market

Kushki MCP server

by codespar·io.github.codespar/mcp-kushki·v0.1.0·271 stars
No reviews yet

MCP server for Kushki — LATAM PSP: card charges, preauth, PSE/SPEI transfer, cash, subscriptions

B82/100grade B
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
B82/100

full report

Adoption
Growing

271 stars12 downloads/wk

Reviews

Write one

Nobody has reviewed Kushki yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Kushki tools (10, 8 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • cancel_subscriptionwrite action

    Cancel a subscription (DELETE /card/v1/subscriptions/{subscriptionId}, private merchant id). Stops all future charges.

  • capture_preauthorization

    Two-step charge, step 2: capture a previous preauthorization (POST /card/v1/capture, private merchant id). Amount may be lower than the preauth (partial capture).

  • create_cash_chargewrite action

    Cash payment reference (POST /cash/v1/charges, private merchant id). Generates a voucher/reference the customer pays at a cash network (OXXO-style). Returns reference + expiry.

  • create_chargewrite action

    One-step card charge (POST /card/v1/charges, private merchant id). Pass the token from tokenize_card plus the amount object. Supports metadata, months (MX installments) and deferred (installment plans).

  • create_preauthorizationwrite action

    Two-step charge, step 1: hold funds on the card (POST /card/v1/preAuthorization, private merchant id). Returns a ticketNumber to capture later.

  • create_subscriptionwrite action

    Recurring card subscription (POST /card/v1/subscriptions, private merchant id). Kushki charges the tokenized card on the given periodicity until cancelled.

  • create_transfer_chargewrite action

    Bank transfer-in charge with a transfer token (POST /transfer/v1/init, private merchant id). Returns the bank redirect URL the customer authorizes at.

  • create_transfer_tokenwrite action

    Token for a bank-transfer-in (POST /transfer/v1/tokens, public merchant id). PSE in Colombia, SPEI in Mexico, bank transfer in Chile/Peru. Feeds create_transfer_charge.

  • tokenize_card

    Exchange raw card data for a single-use token (POST /card/v1/tokens, public merchant id). The token feeds create_charge / create_preauthorization / create_subscription. Card data never touches your backend.

  • void_chargewrite action

    Void / refund a card charge (DELETE /card/v1/charges/{ticketNumber}, private merchant id). Same-day = void; settled = refund. Optional partial amount where the acquirer supports it.

Public scan report

scanner v0.1.9 · 2026-09-26 · same rubric, same numbers if you re-run it

no findings
  • Code scan3 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitystatic API keys via environment variables6/15
  • Maintenancelast push 28 days ago15/15
  • Maintainer identityregistry namespace matches repository owner7/10
Overall 82/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Kushki compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
82/100
higher than 63% of 48,255 servers
Tools
10
the typical server has 7
Tools that change things
80%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
271
more than 95% of 28,688 servers
Downloads a week
12
more than 3% of 12,191 servers with a package

What its tools let an agent do: 2 read · 6 create · 1 change · 1 delete

Install Kushki in Claude Code, Cursor or VS Code

Runs npx -y @codespar/mcp-kushki on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add mcp-kushki -- npx -y @codespar/mcp-kushki
Add to Cursor

What the publisher says

From the Kushki repository's README, as published. We do not edit it. Read it on GitHub

MCP Dev LATAM 🌎 Every commerce API your AI agent needs to run a business in Latin America. Brazil 🇧🇷 · Mexico 🇲🇽 · Argentina 🇦🇷 · Colombia 🇨🇴 · Chile 🇨🇱 · Peru 🇵🇪 · plus 4 agentic payment protocols. MCP servers for LATAM commerce · live in the official MCP Registry · MIT License Machine-readable catalog: codespar.dev/api/servers Catalog · Quick Start · Agentic Protocols · All Servers · Contribute

The Problem

AI agents can write code, analyze data, and chat. But they can't operate a business — collect payments, issue invoices, ship products, or notify customers. Especially not in Latin America, where every service has its own API, auth pattern, and quirks (mTLS for BACEN Pix v2, JWT-RSA for STP-SPEI, AFIP web services, contract-gated developer portals, and on).

Meanwhile, four agentic payment protocols are shipping in parallel — checkout protocols (Stripe ACP, Google UCP), authorization layers (AP2), and micropayment rails (x402) — and none of them compose cleanly with each other or with the regional rails businesses actually run on.

MCP Dev LATAM bridges both gaps. Traditional LATAM services + the new agentic payment protocols, all accessible through a single MCP interface.

The Solution

Each MCP server in this repo wraps a real provider — payments, fiscal, logistics, messaging, banking, ERP, identity, fraud, crypto, and the agentic protocols — so your agent can operate a complete business workflow.

🛒 Customer places order
  → 💳 Agent charges via Pix (Asaas / Mercado Pago / Zoop)
  → 📄 Agent issues NFe (Nuvem Fiscal / Focus NFe / NFe.io)
  → 📦 Agent generates shipping label (Melhor Envio / Skydropx)
  → 📱 Agent sends tracking via WhatsApp (Z-API / WhatsApp Cloud)
  → 📊 Agent records in ERP (Omie / Bling / Tiny)
  → 🏦 Agent reconciles balance (Stark Bank / Itaú / BTG)

Six systems. Zero human intervention. One agent.

Agentic Payment Protocols

Four servers for the emerging agentic payment stack:

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Kushki: common questions

Is Kushki MCP server safe?
Mostly: it is graded B (82/100). Read the Kushki safety report
How do I install Kushki?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Kushki need an API key?
Yes. The registry entry asks for KUSHKI_PUBLIC_MERCHANT_ID, KUSHKI_PRIVATE_MERCHANT_ID.
Is Kushki maintained?
The last commit was 67 days ago (2026-08-29). The latest release is v0.1.0.
How does Kushki compare with other MCP servers?
safety score 82/100 (higher than 63% of 48,255 servers); tools 10 (the typical server has 7); tools that change things 80% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

More from codespar →