convez.ai
MCP ServerIntegração & APIsIntermediário
unixlamadev-spec

LightningProx MCP

unixlamadev-spec/lightningprox-mcp

Acesso a IA pay-per-request via Lightning, sem contas nem chaves API

Ver no GitHub
InicialPluginScore · de 0 a 100

Servidor MCP que integra acesso a 19 modelos de IA (Anthropic, OpenAI, Together.ai, Mistral, Google) através de pagamentos via Bitcoin Lightning, sem contas ou chaves API. Carregue um token de gastos e consulte modelos com suporte a visão/multimodal pagando por requisição em sats.

Instalação

$npx convez-ai unixlamadev-spec/lightningprox-mcp

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
2
Forks
0
Acompanhando
0
Saúde
57%
Último commit
há 2 semanas
Versão
v1.3.0
Issues abertas
1
Contribuidores
1

Casos de uso

  • Consultoria a modelos de IA sem vincular cartão de crédito ou gerenciar chaves API
  • Análise de imagens e multimodal com pagamento instantâneo em sats
  • Integração modular em aplicações Node.js que precisam de flexibilidade em provedores de IA
  • Prototipagem e testes rápidos de múltiplos modelos com micropagamentos

Veredito

MCP bem arquitetado que democratiza acesso a IA via Lightning Network, eliminando fricção de contas e chaves. Ideal para quem quer experimentar múltiplos modelos sem overhead administrativo, embora exija familiaridade com wallets Bitcoin.

README

A tradução para o português deste README ainda está na fila.

lightningprox-mcp

MCP server for LightningProx — pay-per-request AI via Bitcoin Lightning. No accounts, no API keys. Load a spend token, start querying.

Install

npx lightningprox-mcp

What LightningProx Is

LightningProx is an AI gateway that accepts Bitcoin Lightning payments instead of API keys. You load a prepaid spend token, pass it in the X-Spend-Token header, and each request is deducted from your balance in sats. No signup, no monthly plan, no credentials to manage.

19 models across 5 providers:

ProviderModels
Anthropicclaude-opus-4-6, claude-sonnet-4-6, claude-haiku-4-5
OpenAIgpt-4o, gpt-4-turbo, gpt-4o-mini
Together.aillama-4-maverick, llama-3.3-70b, deepseek-v3, mixtral-8x7b
Mistralmistral-large-latest, mistral-medium, mistral-small, codestral, devstral, magistral
Googlegemini-2.5-flash, gemini-2.5-pro

Vision / multimodal: Pass image_url directly in your request. URL mode only — no base64 encoding required.

Setup

Claude Desktop

{
  "mcpServers": {
    "lightningprox": {
      "command": "npx",
      "args": ["lightningprox-mcp"]
    }
  }
}

Config location:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
  • Linux: ~/.config/claude/claude_desktop_config.json

Claude Code

claude mcp add lightningprox -- npx lightningprox-mcp

Tools

ToolDescription
ask_aiSend a prompt to any model, authenticated via spend token. Pass model to select (e.g. gemini-2.5-flash, mistral-large-latest, claude-sonnet-4-6).
ask_ai_visionSend a prompt with an image URL for multimodal analysis
check_balanceCheck remaining sats on a spend token
list_modelsList available models with per-call pricing
get_pricingEstimate cost in sats for a given model and token count
get_invoiceGenerate a Lightning invoice to top up a spend token

Spend Token Auth

Every request authenticates via the X-Spend-Token header:

curl -X POST https://lightningprox.com/v1/chat \
  -H "Content-Type: application/json" \
  -H "X-Spend-Token: lnpx_your_token_here" \
  -d '{
    "model": "claude-sonnet-4-6",
    "messages": [{"role": "user", "content": "What is the Lightning Network?"}]
  }'

For vision requests, include image_url in the message content — no base64 needed:

curl -X POST https://lightningprox.com/v1/chat \
  -H "Content-Type: application/json" \
  -H "X-Spend-Token: lnpx_your_token_here" \
  -d '{
    "model": "claude-sonnet-4-6",
    "messages": [{
      "role": "user",
      "content": [
        {"type": "image_url", "image_url": {"url": "https://example.com/chart.png"}},
        {"type": "text", "text": "Describe this chart"}
      ]
    }]
  }'

Getting a Spend Token

  1. Call get_invoice (or ask_ai without a token) to receive a Lightning invoice
  2. Pay the invoice from any Lightning wallet
  3. Your spend token is returned — use it for all subsequent requests until balance runs out

Endpoints

EndpointDescription
POST /v1/chatChat completions — OpenAI-compatible format
POST /v1/messagesAnthropic messages format
GET /v1/modelsList available models with pricing
GET /v1/balanceCheck spend token balance
POST /v1/invoiceGenerate Lightning invoice

Links

Built by LPX Digital Group LLC

Ver o original no GitHub

Bom para

Relacionados