Sats4ai MCP Server

sats4ai-mcp

The permissionless communication supercharger for AI agents. 40+ tools paid with Bitcoin Lightning. No signup, no API keys, no KYC.

A remote MCP (Model Context Protocol) server that gives AI agents access to AI phone calls in any language, voice in 602 languages, translation across 119, fax, SMS, transcription, audiobooks, image generation, music, document extraction, and more — all paid per-use with Lightning Network micropayments.

Quick Setup

Claude Desktop

Add to your claude_desktop_config.json (~/Library/Application Support/Claude/claude_desktop_config.json on macOS, %APPDATA%\Claude\claude_desktop_config.json on Windows):

{
  "mcpServers": {
    "sats4ai": {
      "url": "https://sats4ai.com/api/mcp"
    }
  }
}

Claude Code

claude mcp add sats4ai --transport http https://sats4ai.com/api/mcp

Verify the connection: ask the agent "list the first 3 Sats4AI models" — it should call list_models and return results. For agents that pay invoices autonomously, also add a Lightning wallet MCP (see Payment via Agent Wallets).

Cursor

Settings → MCP → Edit Config, then add:

{
  "mcpServers": {
    "sats4ai": {
      "url": "https://sats4ai.com/api/mcp"
    }
  }
}

Restart Cursor. In a new chat, ask "what Sats4AI tools are available?" to confirm tool discovery. For autonomous payments, pair with a Lightning wallet MCP (see Payment via Agent Wallets).

Windsurf

Edit ~/.codeium/windsurf/mcp_config.json (create it if missing). Important: Windsurf uses serverUrl (not url) for remote HTTP MCP servers:

{
  "mcpServers": {
    "sats4ai": {
      "serverUrl": "https://sats4ai.com/api/mcp"
    }
  }
}

Restart Windsurf. Sats4AI tools appear in the Cascade tool list. Cascade has a 100-tool cap across all MCPs, so keep the active set lean. For autonomous payments, pair with a Lightning wallet MCP (see Payment via Agent Wallets).

stdio proxy (legacy MCP clients)

For clients that don't support remote HTTP servers, use the bundled stdio proxy:

npx sats4ai-mcp

Or in your config:

{
  "mcpServers": {
    "sats4ai": {
      "command": "npx",
      "args": ["sats4ai-mcp"]
    }
  }
}

Any MCP Client

The server URL is:

https://sats4ai.com/api/mcp

This is a remote HTTP server — no local process, no dependencies, no installation needed.

What Can It Do?

Once connected, just ask your agent. These prompts exercise the full flow — discover, pay the Lightning invoice, get the result:

• "Translate this paragraph to Spanish with Sats4AI — create the payment, pay the invoice with my lightning wallet, then run the translation."
• "Check what an SMS to +33612345678 costs, then send it: 'Your appointment is confirmed for 3pm tomorrow.'"
• "Generate an image of a lighthouse in a thunderstorm — pay the invoice and show me the result."
• "Send an AI voice agent to call +14155551234 and reschedule my dentist appointment, then give me the transcript."
• "Turn this EPUB into an audiobook — create the payment, then poll check_job_status until it's done."
• "Remove the background from this image."
• "Transcribe this audio file, then translate the transcript to English."
• "Get a quote for faxing this 3-page PDF to +4930123456, then send it."

Available Tools

AI Generation

Audio & Speech

Image Processing

Vision & Documents

Communication

Helper Tools

How It Works

1. Agent calls list_models to discover available models and pricing
2. Agent calls create_payment — gets a Lightning invoice
3. Payment is made via the agent's Lightning wallet (e.g., lightning-wallet-mcp)
4. Agent calls the tool (e.g., image, text) with the paymentId
5. Result is returned — base64 image, text, URL, etc.

No API keys. No accounts. No rate limits tied to identity. Just Bitcoin and AI.

Error Handling & Refunds

When a paid tool fails after payment, the JSON-RPC error response includes refund information:

{
  "jsonrpc": "2.0",
  "id": 1,
  "error": {
    "code": -32603,
    "message": "Image generation failed",
    "data": {
      "refund": {
        "charge_id": 12345,
        "refund_amount": 200,
        "lnurl_withdraw": "lnurl1dp68gurn8ghj7..."
      }
    }
  }
}

Claim the refund using any LNURL-compatible wallet or the claim_lnurl_withdraw tool from lightning-wallet.

Errors also carry an error_code plus a recovery suggestion in error.data. Payment-lifecycle codes: PAYMENT_NOT_FOUND (wrong paymentId), PAYMENT_PENDING (invoice not paid yet), PAYMENT_ALREADY_USED (each payment covers one call). Full catalog: GET https://sats4ai.com/api/error-codes.

Payment via Agent Wallets

Pair with a Lightning wallet MCP server so your agent can pay autonomously:

{
  "mcpServers": {
    "sats4ai": {
      "url": "https://sats4ai.com/api/mcp"
    },
    "lightning-wallet": {
      "command": "npx",
      "args": ["lightning-wallet-mcp"]
    }
  }
}

The agent uses lightning-wallet to pay invoices from sats4ai, enabling fully autonomous AI tool usage.

L402 API

For direct HTTP integration without MCP, use the L402 API:

# Step 1: Request -> get 402 + Lightning invoice
curl -X POST https://sats4ai.com/api/l402/generate-image \
  -H "Content-Type: application/json" \
  -d '{"input": {"prompt": "a cat in space"}}' -i

# Step 2: Pay the invoice with any Lightning wallet

# Step 3: Re-send with proof
curl -X POST https://sats4ai.com/api/l402/generate-image \
  -H "Content-Type: application/json" \
  -H "Authorization: L402 <macaroon>:<preimage>" \
  -d '{"input": {"prompt": "a cat in space"}}'

Or skip the manual steps entirely: our L402 endpoints speak the standard L402 protocol, so lnget — Lightning Labs' own L402 client — pays them automatically. Point it at your Lightning node and call the endpoint:

lnget -X POST -d '{"text": "Hello", "targetLanguage": "Spanish"}' \
  --content-type application/json --max-cost 50 \
  https://sats4ai.com/api/l402/translate-text
# Fetches the 402, pays the invoice, retries, prints the result.

Full L402 docs: sats4ai.com/l402 | Code examples: sats4ai-l402-examples

Service Discovery

Machine-readable endpoints for agent discovery:

# Full service catalog with pricing, quality benchmarks, and performance metadata
GET https://sats4ai.com/.well-known/l402-services

# MCP tool catalog with latency (p50/p95), reliability, and failure modes
GET https://sats4ai.com/api/mcp/discovery

# Semantic search — find tools by capability
GET https://sats4ai.com/api/discover?q=translate

# Per-service metadata with enums and input schemas
GET https://sats4ai.com/api/l402/{service}

Every paid tool includes performance metadata (latency p50/p95, reliability rating, known failure modes) so agents can make informed decisions about which tools to call and how long to wait.

Programmatic Usage

const { SERVER_URL, TOOLS, getClaudeConfig } = require("sats4ai-mcp");

console.log(SERVER_URL);       // "https://sats4ai.com/api/mcp"
console.log(TOOLS);            // ["image", "video", "text", ...]
console.log(getClaudeConfig()) // { mcpServers: { sats4ai: { url: "..." } } }

Security

Found a vulnerability? Do not open a public issue. Email sats4ai@gmail.com. See SECURITY.md for full disclosure policy and scope.

Links

• Website: sats4ai.com
• MCP Docs: sats4ai.com/mcp
• L402 API Docs: sats4ai.com/l402
• L402 Code Examples: github.com/cnghockey/sats4ai-l402-examples
• Service Discovery: sats4ai.com/.well-known/l402-services
• Semantic Search: sats4ai.com/api/discover
• Security Policy: SECURITY.md

License

MIT