MCP.Market

Culqi MCP server

by codespar·io.github.codespar/mcp-culqi·v0.2.2·271 stars

MCP server for Culqi — Peru PSP: charges, refunds, cards, Yape/PagoEfectivo, subscriptions

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

full report

Adoption
Growing

271 stars

Reviews

Write one

Nobody has reviewed Culqi yet.

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

Culqi tools (20, 14 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 an active subscription (DELETE /subscriptions/{id}).

  • capture_chargewrite action

    Capture a previously-authorized charge (POST /charges/{id}/capture). Use after creating a charge with capture=false. Must be called within 10 days of authorization.

  • confirm_orderwrite action

    Confirm an unpaid order (POST /orders/{id}/confirm). Moves the order to a confirmed state ready to be paid by the customer via Yape / PagoEfectivo.

  • create_cardwrite action

    Attach a tokenized card to a customer for reuse (POST /cards). Returns a card id (crd_xxx) usable as source_id on future charges.

  • create_chargewrite action

    Create a charge (POST /charges). Amount is in cents of the currency (e.g. 1000 = S/ 10.00 PEN). source_id accepts a token id (tkn_xxx) or a stored card id (crd_xxx).

  • create_customerwrite action

    Create a customer record (POST /customers). Use the returned customer_id with create_card to save reusable cards.

  • create_orderwrite action

    Create an order (POST /orders) for non-card payment methods — Yape, PagoEfectivo (Cash), bank transfer. Returns an order with CIP / QR data the payer uses to complete payment. Confirm reception via webhooks or confirm_order.

  • create_planwrite action

    Create a subscription plan (POST /plans). Plans are reusable templates — attach customer cards via create_subscription.

  • create_subscriptionwrite action

    Subscribe a customer's saved card to a plan (POST /subscriptions). Requires tyc=true (terms & conditions acceptance).

  • create_tokenwrite action

    Tokenize a card (POST /tokens). Returns a token id like tkn_xxx. Tokenization is typically done client-side via culqi.js or mobile SDKs; this tool is primarily for test scripts and integration tests. Never send real PANs from a backend without PCI scope.

  • delete_cardwrite action

    Detach a saved card from its customer (DELETE /cards/{id}). The card id becomes unusable as source_id afterwards.

  • get_chargewrite action

    Retrieve a charge by Culqi id.

  • get_customer

    Retrieve a customer by Culqi id (GET /customers/{id}).

  • get_event

    Retrieve a single webhook event by id (GET /events/{id}). Useful for auditing a webhook delivery against Culqi's canonical record.

  • get_refundwrite action

    Retrieve a refund by id (GET /refunds/{id}).

  • list_charges

    List charges (GET /charges) with optional filters. Filters are passed as query params: amount, min_amount, max_amount, installments, currency_code, code (auth code), decline_code, fraud_score, first_name, last_name, email, country_code, creation_date_from (ms), creation_date_to (ms), limit, before, after.

  • list_customers

    List customers (GET /customers) with optional filters passed as query params: first_name, last_name, email, country_code, creation_date_from (ms), creation_date_to (ms), limit, before, after.

  • list_events

    List webhook events (GET /events) with optional filters. Filters are passed through as query params: event_type, creation_date_from, creation_date_to, limit, before, after.

  • list_orders

    List orders (GET /orders) with optional filters passed as query params: order_number, state (created, paid, expired, deleted, failed), creation_date_from (ms), creation_date_to (ms), limit, before, after.

  • refund_chargewrite action

    Refund a captured charge (POST /refunds). Partial refunds supported by setting amount below the charge total.

Public scan report

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

no findings
  • Code scan5 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 29 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 Culqi 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
20
the typical server has 7
Tools that change things
70%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
271
more than 95% of 28,688 servers

What its tools let an agent do: 6 read · 7 create · 5 change · 2 delete

Install Culqi in Claude Code, Cursor or VS Code

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

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

What the publisher says

From the Culqi 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.

Culqi: common questions

Is Culqi MCP server safe?
Mostly: it is graded B (82/100). Read the Culqi safety report
How do I install Culqi?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Culqi need an API key?
Yes. The registry entry asks for CULQI_SECRET_KEY.
Is Culqi maintained?
The last commit was 67 days ago (2026-08-29). The latest release is v0.2.2.
How does Culqi compare with other MCP servers?
safety score 82/100 (higher than 63% of 48,255 servers); tools 20 (the typical server has 7); tools that change things 70% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

More from codespar →