Safefy MCP
Official MCP server for Safefy, enabling AI agents to manage PIX payments, withdrawals, customers, and transactions via the Safefy payment API.
README
Safefy MCP
MCP server oficial da Safefy — integre cobranças PIX, saques, clientes e pagamentos diretamente em qualquer agente de IA compatível com Model Context Protocol.
Como usar no seu agente de IA
Claude (claude.ai)
Configure via claude_desktop_config.json:
{
"mcpServers": {
"safefy": {
"command": "npx",
"args": ["-y", "@safefypay/safefy-mcp"]
}
}
}
v0 (v0.dev)
No chat do v0, clique em "+" → "Add MCP Server" e configure:
{
"name": "safefy",
"command": "npx",
"args": ["-y", "@safefypay/safefy-mcp"]
}
Lovable (lovable.dev)
Acesse Settings → MCP Servers → Add Server e cole:
{
"name": "safefy",
"command": "npx",
"args": ["-y", "@safefypay/safefy-mcp"]
}
Cursor / Windsurf / VS Code
Adicione ao seu mcp.json ou settings.json:
{
"mcpServers": {
"safefy": {
"command": "npx",
"args": ["-y", "@safefypay/safefy-mcp"]
}
}
}
Após adicionar o servidor, peça ao agente para configurar suas credenciais:
"Configure minhas credenciais Safefy: public key
pk_..., secret keysk_..."
Gere suas credenciais em: https://app.safefypay.com.br/panel/merchant/api-credentials
O que este servidor expõe
- Assistente de integração:
- via
SDK Node(safefy-sdk-node) - via
API direta(qualquer linguagem)
- via
- Configuração/autenticação de credenciais (
/v1/auth/token) - Saldo (
/v1/balance) - Transações (
/v1/transactions) - Saques (
/v1/cashouts) - Clientes (
/v1/customers) - Pedidos (
/v1/orders) - Produtos (
/v1/products) - Payment Links públicos (
/v1/payment-links) - Requisição genérica para cobertura total da API (
safefy_payment_api_request)
Requisitos
- Node.js 18+
- Credenciais de API Payment (
Public KeyeSecret Key) - Gere no painel: https://app.safefypay.com.br/panel/merchant/api-credentials
Instalação local (desenvolvimento)
npm install
npm run build
npm start
Principais tools
safefy_payment_get_integration_guidesafefy_payment_list_capabilitiessafefy_payment_configure_credentialssafefy_payment_get_configurationsafefy_payment_authenticatesafefy_payment_api_requestsafefy_payment_get_balancesafefy_payment_create_transactionsafefy_payment_list_transactionssafefy_payment_get_transactionsafefy_payment_simulate_transactionsafefy_payment_resend_transaction_webhooksafefy_payment_create_cashoutsafefy_payment_list_cashoutssafefy_payment_get_cashoutsafefy_payment_cancel_cashoutsafefy_payment_simulate_cashoutsafefy_payment_create_customersafefy_payment_list_customerssafefy_payment_get_customersafefy_payment_update_customersafefy_payment_create_ordersafefy_payment_list_orderssafefy_payment_get_ordersafefy_payment_list_productssafefy_payment_get_productsafefy_payment_get_payment_linksafefy_payment_start_payment_linksafefy_payment_get_payment_link_status
Cobertura total da API Payment
Quando uma operação ainda não tiver tool dedicada, use safefy_payment_api_request.
Exemplo:
{
"path": "/v1/transactions",
"method": "GET",
"requireAuth": true,
"query": {
"page": 1,
"pageSize": 20
}
}
Skill no .github
O conteúdo de mcp-builder foi espelhado para .github/skills/mcp-builder para uso como skill de apoio no projeto.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.