Lightningprox MCP

Community AI and agents

Pay-per-request AI access via Bitcoin Lightning through LightningProx, with vision and multimodal support.

Install

The installation steps are in the documentation below. Documentation

Documentation

From the project's README on GitHub, refreshed weekly. Links open on GitHub.

Contents
  1. lightningprox-mcp
  2. Install
  3. What LightningProx Is
  4. Setup
  5. Tools
  6. Spend Token Auth
  7. Getting a Spend Token
  8. Endpoints
  9. Links

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

Built by LPX Digital Group LLC

Frequently asked questions

What is Lightningprox MCP?

Pay-per-request AI access via Bitcoin Lightning through LightningProx, with vision and multimodal support.

How do I install Lightningprox MCP?

Follow the installation steps in its documentation, shown on this page and in its repository.

Is Lightningprox MCP open source?

Yes. Its code is on GitHub under the MIT license.

Who maintains Lightningprox MCP?

It is published by unixlamadev-spec. AI.tn lists it but does not maintain or endorse it.

From the community awesome-mcp-servers lists and the project's GitHub repository. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.