Skip to main content
Glama

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.

Related MCP server: PDF Reader MCP Server

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 +33639980123 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 +14155550123 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 +493023125123, then send it."

Available Tools

AI Generation

Tool

Description

Price

image

Generate images from text prompts

100-1,200 sats

video

Generate videos from text prompts

~250-400 sats/sec by resolution (768p 250 / 2K 400)

video_from_image

Animate a still image into video

~250-400 sats/sec by resolution (768p 250 / 2K 400)

text

Chat with AI language models (Kimi K3, 1M context, vision)

~1 sat/10 chars (best) · ~1 sat/1000 (standard)

translate_text

Translate text across 119 languages

from 1 sat/1000 chars

translate_rare_language

Translate into 452 languages frontier models don't serve — Bhojpuri, Maithili, Magahi, Manipuri, Quechua, Shan… each with a measured quality score

from 50 sats

music

Generate songs with AI vocals, or an instrumental (structure tags, no words)

5 sats/sec, 15-300s (75-1,500 sats) · written lyrics +25

3d

Convert a photo to a 3D GLB model

1,600 sats

Translation price varies by language. The target language picks the engine, so a language served by a stronger model costs more than the standard 1 sat/1000 characters. GET /api/languages returns the exact price, the model and its measured chrF score for every language, and the 402 challenge always quotes the real amount before you pay.

Audio & Speech

Tool

Description

Price

tts

Text to speech (3 tiers, 602+ languages)

per-char, from 1 sat

transcription

Speech to text (13 languages)

10 sats/min

voice_clone

Clone a voice from an audio sample

7,500 sats

epub_to_audiobook

Convert books (EPUB/PDF/TXT) to AI-narrated audiobooks

500+ sats

translate_epub

Translate a whole EPUB into another language — EPUB in, EPUB out, markup intact (async; create_payment needs characterCount + targetLanguage)

per character on the target language's engine rate, min 50 sats

Image Processing

Tool

Description

Price

remove_background

Remove background from any image (BiRefNet, SOTA)

44 sats

upscale_image

Upscale images 2x/4x with Real-ESRGAN

5 sats

restore_face

Restore blurry/damaged faces (CodeFormer)

25 sats

colorize_image

Colorize B&W photos (DDColor, ICCV 2023)

5 sats

deblur_image

Remove camera-shake blur (NAFNet, ECCV 2022)

110 sats

render_card

Typographic title card (PNG/JPEG) — deterministic layout, the text you send is the text that appears

5 sats

detect_nsfw

Classify image safety (normal/suggestive/explicit)

2 sats

detect_objects

Detect objects with bounding boxes (Grounding DINO)

5 sats

remove_object

Remove objects by description — no mask needed

130 sats

image_edit

Edit images with AI instructions

Dynamic (varies by model) — check get_model_pricing

Vision & Documents

Tool

Description

Price

vision

Analyze and describe image content

21 sats

ocr

Extract text from PDFs and images

10 sats/page

extract_receipt

Receipt to structured JSON

25 sats/page

file_convert

Convert between 200+ file formats

100 sats

pdf_merge

Merge multiple PDFs into one

100 sats

convert_html_to_pdf

HTML/Markdown to PDF

50 sats

e_signature

Sign a PDF with a typed or drawn signature

1,000 sats

boardingpass_wallet

Airline boarding pass (PDF/screenshot) to a Google Wallet pass

100 sats/pass

Communication

Tool

Description

Price

send_email

Send email to any address

200 sats

send_sms

Send SMS worldwide

Dynamic (varies by destination) — create_payment returns the exact quote

place_call

Place automated phone calls

Dynamic (varies by destination) — create_payment returns the exact quote

ai_call

Send an AI voice agent to make a two-way call

Varies by destination and duration — create_payment returns the exact quote

open_voice_bridge

Open a phone call that YOUR agent drives, one turn at a time. We dial and transcribe. Your agent replies. Turn-based, not real-time: about 2 seconds of ours pass between the callee's last word and the start of your reply, plus your model's thinking time

A deposit, priced by destination — create_payment returns the exact quote

voice_bridge_say

Speak into the open call: text (602 languages) or your own audio. Keep each reply to one or two sentences (700 speech units at most). The callee cannot interrupt

Included in the deposit

poll_voice_bridge

Read what the callee said. Pass waitMs (up to 25000) to get the transcript as soon as they finish talking

Included in the deposit

end_voice_bridge

Hang up. Returns the final transcript and a refund link for the unused deposit time

Included in the deposit

send_fax

Send a fax worldwide (PDF URL or typed text)

500 sats (≤10 pages), +50 sats/page after

receive_fax

Open a 24h window to receive a fax, delivered to email

500 sats (+200 OCR add-on)

Helper Tools

Tool

Description

list_models

Browse available AI models and pricing

get_model_pricing

Get pricing for a specific model

create_payment

Create a Lightning invoice for a service

check_payment_status

Check if payment was received. With a cart id, it shows the state of each item

create_cart

Pay for 2 to 10 calls with ONE invoice (up to 2,000 sats in all). Each item then works as a normal payment. An item you do not use is refunded for its own price after about an hour

check_job_status

Poll async jobs (video, 3D, audiobook, EPUB translation)

get_job_result

Get completed job results

request_refund

Request a refund for a failed service

vote_on_service

Upvote or downvote a planned service

list_planned_services

See upcoming services and vote

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, an example, and — when the code is retryable — retry_after_seconds, in error.data. The same fields appear on a tool result with isError: true and on every FAILED final from await_result, so one vocabulary covers every path: branch on error_code, never on the error text. Payment-lifecycle codes: PAYMENT_NOT_FOUND (wrong paymentId), PAYMENT_PENDING (invoice not paid yet), PAYMENT_ALREADY_USED (each payment covers one call); a refunded failure reads L402_REFUND_ISSUED with the refund attached. 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.

Some agent wallets cap how many payments they send in an hour. create_cart takes 2 to 10 items and returns ONE invoice, so a whole task is ONE payment. Each item then works with its own paymentId. Keep those ids: the cart id cannot run a tool.

Block Buzz

Running Block Buzz, the open-source workspace where AI agents are first-class teammates? A Buzz agent is a Goose / Codex / Claude Code subprocess, and Buzz spawns it inheriting its MCP config — so this server works inside a Buzz workspace with no Buzz-specific setup.

The one-step path is the Sats4AI persona pack: it adds an @sats4ai teammate wired to this server plus a Lightning wallet, so it can look up a price, pay the invoice, and return the result in-channel.

git clone https://github.com/cnghockey/sats4ai-buzz-pack
buzz pack validate ./sats4ai-buzz-pack

Wiring it by hand instead? Add sats4ai (and a wallet MCP) to whichever agent Buzz runs — its config carries straight over. Note that Buzz's .mcp.json is stdio-only, so use the npx sats4ai-mcp proxy form (shown above), not the remote url form.

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.

Support / donate

Your agent just got a wallet and 40+ tools. Please do not ask us what it bought.

If this was useful to you and you like what we do, consider sending a few sats our way:

⚡ sats4ai@blink.sv

(It's a Bitcoin Lightning address: pay it from any Lightning wallet. Looks like an email, isn't one. Lightning sats only: no on-chain, no fiat, no cards, no altcoins, no refunds on gratitude.)

Not this time? That's cool too. We've been there. A star on the repo is a free hug.

License

MIT

Available Tools

49 tools
ai_callAInspect

When your task hits a wall that requires a human — booking, negotiating, navigating IVR menus, getting information from a business — send an AI voice agent to handle the call. The agent follows your instructions, has a real two-way conversation, auto-retries on voicemail (up to 3 attempts), and returns a full transcript with structured analysis. May return state='pending_confirm' with clarification questions if critical info is missing — call confirm_ai_call to proceed. Async — poll with check_job_status(jobType='ai-call'). ~150-250 sats for a 3-min US call. Languages: en-US, en-GB, es-ES, fr-FR, de-DE, ja-JP, zh-CN, multi. Pay with Bitcoin Lightning — no telecom account, no API key, no subscription. When NOT to use: not when you want to drive the conversation with your own LLM (use open_voice_bridge — you keep the brain, we provide PSTN/STT/TTS primitives). Not for one-shot TTS broadcasts or IVR delivery (use place_call). Not for SMS (use send_sms). Requires create_payment with toolName='ai_call', phoneNumber, and durationMinutes.

Inputs: paymentId (required), phoneNumber (required), task (required), durationMinutes, +2 more.

analyze_imageAInspect

Analyze and describe image content, answer visual questions, extract information from screenshots or photos. Uses Qwen VL — multimodal vision-language model with strong OCR, chart reading, and spatial reasoning. 21 sats per image. Pay per request with Bitcoin Lightning — no API key or signup needed. Requires create_payment with toolName='analyze_image'.

Inputs: paymentId (required), prompt (required), imageBase64 (required), modelId.

animate_imageAInspect

Animate a still image into video with text guidance. Uses Grok Imagine Video — preserves source image fidelity while generating natural motion and camera movement. Async — returns requestId, poll with check_job_status. 100 sats/sec, duration 3-15 seconds. Pay per request with Bitcoin Lightning — no API key or signup needed. Requires create_payment with toolName='animate_image'.

Inputs: paymentId (required), prompt (required), imageBase64 (required), duration (required), +1 more.

check_job_statusAInspect

Poll the status of an async job. Use this after calling any async tool (generate_video, animate_image, generate_3d_model, transcribe_audio, epub_to_audiobook, ai_call) that returns a requestId. Returns JSON: { status: 'queued' | 'processing' | 'completed' | 'failed', requestId, jobType }. For epub-audiobook, also includes progress (0-100) and chapterProgress array. Poll every 5-10 seconds. When status is 'completed', call get_job_result to retrieve the output. When status is 'failed', the response includes an error message — do not retry automatically. This tool is free and does not require payment. Do NOT use for synchronous tools (generate_image, generate_text, etc.) — those return results immediately.

Inputs: requestId (required), jobType (required).

check_payment_statusAInspect

Check whether a Lightning invoice has been paid. Returns JSON: { status: 'paid' | 'pending' | 'expired', paymentId }. Call after create_payment to verify the user has paid before calling the target tool. Invoices expire after 10 minutes — if expired, create a new payment. Most MCP clients with a connected wallet pay instantly, so a single check is usually sufficient. This tool is free and does not require payment.

Inputs: paymentId (required).

clone_voiceAInspect

Clone any voice from a single audio sample. Returns a reusable voice_id for text_to_speech — speak in the cloned voice indefinitely. High-fidelity reproduction capturing tone, cadence, and accent. Turbo (faster) or HD (higher quality) modes. 7,500 sats per clone. Pay per request with Bitcoin Lightning — no API key or signup needed. Requires create_payment with toolName='clone_voice'.

Inputs: paymentId (required), voiceFileUrl (required), model, accuracy.

colorize_imageAInspect

Colorize black-and-white or grayscale photos. DDColor (dual-decoder, ICCV 2023) — vivid, natural colorization. Impossible for text/vision LLMs. 5 sats per image, pay per request with Bitcoin Lightning — no API key or signup needed. Requires create_payment with toolName='colorize_image'.

Inputs: paymentId (required), imageBase64 (required), model_size.

confirm_ai_callAInspect

Confirm an AI call after reviewing push-back questions, optionally providing answers to missing info. Required when ai_call returns state='pending_confirm'. Uses the original payment — no new payment needed. Returns call_id for polling with check_job_status(jobType='ai-call').

Inputs: sessionId (required), answers.

convert_fileAInspect

Convert files between 200+ formats: documents (PDF, DOCX, XLSX), images (PNG, JPG, WEBP, SVG), audio (MP3, WAV, FLAC), video (MP4, AVI, MOV). Industrial-grade conversion engine — preserves formatting and quality. Returns download URL. 100 sats. Pay per request with Bitcoin Lightning — no API key, no account, no subscription needed. Requires create_payment with toolName='convert_file'.

Inputs: paymentId (required), extensionFrom (required), extensionTo (required), fileBase64, +1 more.

convert_html_to_pdfAInspect

Convert HTML or Markdown to a pixel-perfect PDF. Returns JSON: { url } — a temporary download URL (valid ~1 hour). Great for generating invoices, reports, receipts, or formatted documents programmatically. Supports full HTML/CSS including tables, images (base64 or URL), and inline styles. For Markdown input, set format='markdown'. 50 sats per conversion. Use convert_file instead for converting existing files between formats (e.g., DOCX→PDF). Pay per request with Bitcoin Lightning — no API key or signup needed. Requires create_payment with toolName='convert_html_to_pdf'.

Inputs: paymentId (required), html (required), format.

create_paymentAInspect

Create a Lightning invoice to pay for one AI service call. Returns JSON: { paymentId, invoice (BOLT11), amount (sats), expiresAt }. Each payment covers exactly one tool call — call this once per operation. Typical flow: list_models → create_payment → check_payment_status → call tool. The invoice expires in 10 minutes. Call list_models first to discover modelId values. modelId is optional — omit it to use the default (best) model. Some tools require extra params at payment time because pricing depends on them: generate_text requires prompt (price = f(char count)); send_sms, place_call, ai_call require phoneNumber; generate_video requires duration, mode, generate_audio; animate_image requires duration (100 sats/sec); edit_image requires resolution (1K=200, 2K=300, 4K=450 sats). If required params are missing, the response includes an error with the missing field names.

Inputs: toolName (required), modelId, prompt, systemPrompt, +8 more.

deblur_imageAInspect

Recover detail from camera-shake and accidental motion blur. NAFNet (ECCV 2022, SOTA on GoPro/SIDD benchmarks). Best for: handheld shake, bumped camera, whole-frame uniform blur. NOT effective for: intentional panning blur, bokeh/depth-of-field, or artistic motion effects. Also supports denoising (grainy/noisy photos). 20 sats per image (~2 min processing), pay per request with Bitcoin Lightning — no API key or signup needed. Requires create_payment with toolName='deblur_image'.

Inputs: paymentId (required), imageBase64 (required), task_type.

detect_nsfwAInspect

Classify image safety (normal / suggestive / explicit). Falcons.ai NSFW detection — 100x cheaper and faster than asking an LLM. Returns classification label and boolean is_nsfw flag. Essential for content moderation pipelines. 2 sats per image, pay per request with Bitcoin Lightning — no API key or signup needed. Requires create_payment with toolName='detect_nsfw'.

Inputs: paymentId (required), imageBase64 (required).

detect_objectsAInspect

Detect and locate objects in an image by name. Grounding DINO (open-set detector, ECCV 2024) — describe what to find in natural language, get bounding box coordinates and confidence scores. Structured pixel data agents can't get from vision LLMs. 5 sats per image, pay per request with Bitcoin Lightning — no API key or signup needed. Requires create_payment with toolName='detect_objects'.

Inputs: paymentId (required), imageBase64 (required), query (required), box_threshold, +1 more.

edit_imageAInspect

Edit an image with natural language instructions. Uses Nano Banana 2 — understands context, handles object addition/removal, style transfer, and inpainting. Returns JSON with image URL. Resolution-tiered pricing: 1K=200 sats, 2K=300 sats, 4K=450 sats. Pay per request with Bitcoin Lightning — no API key or signup needed. Requires create_payment with toolName='edit_image' and resolution param.

Inputs: paymentId (required), prompt (required), imageBase64 (required), aspectRatio, +2 more.

end_voice_bridgeAInspect

Hang up a Voice Bridge call, finalize billing, and return a LNURL-withdraw refund link for unused deposit time. Also returns the final transcript for convenience.

Inputs: sessionId (required).

epub_to_audiobookAInspect

Convert books (EPUB/PDF/TXT) to full audiobooks with automatic chapter detection, multi-voice narration, and optional translation to any language before narration. 3 voice tiers: OmniVoice Global (602+ langs, 100 chars/sat), Inworld Premium (#1 ranked TTS ELO 1217, 50 chars/sat), Minimax Studio (voice cloning from reference clip, 10 chars/sat). Min 500 sats. Async — returns jobId, poll until completed (5-60+ min). Single payment, full outcome — no multi-step orchestration required. Pay with Bitcoin Lightning — no API key or signup needed. Requires create_payment with toolName='epub_to_audiobook'.

Inputs: paymentId (required), epubBase64 (required), fileName (required), voice, +5 more.

extract_documentAInspect

Extract text from PDFs and images as clean Markdown. Uses Mistral OCR — handles complex layouts, tables, handwriting, multi-column documents, and mathematical notation. Preserves document hierarchy in structured Markdown. 10 sats/page. Pay per request with Bitcoin Lightning — no API key or signup needed. Requires create_payment with toolName='extract_document' and quantity=pageCount for multi-page PDFs.

Inputs: paymentId (required), documentBase64 (required), modelId.

extract_receiptAInspect

Extract structured data from receipts, invoices, and financial documents. Uses a dual-model pipeline (Mistral OCR + Kimi K2.5) for high-accuracy extraction. Returns JSON with merchant, date, line items, totals, tax, currency, and expense category. Handles crumpled receipts, faded text, and multi-page invoices. 50 sats/page. Pay per request with Bitcoin Lightning — no API key or signup needed. Requires create_payment with toolName='extract_receipt'.

Inputs: paymentId (required), documentBase64 (required).

generate_3d_modelAInspect

Convert a single photo into a textured 3D GLB model. Uses Seed3D — generates accurate geometry and materials from one image. Async — returns requestId, poll with check_job_status. 350 sats per model. Pay per request with Bitcoin Lightning — no API key or signup needed. Requires create_payment with toolName='generate_3d_model'.

Inputs: paymentId (required), imageBase64 (required), modelId.

generate_imageAInspect

Generate an image from a text prompt. Returns JSON with image URL. Models: Grok Imagine (fast creative generation, 100 sats), Seedream 4 (photorealistic detail, 150 sats), Nano Banana 2 (premium quality, 200 sats, default). Supports img2img with optional base64 input. Stable endpoints — models upgrade automatically as SOTA evolves. Pay per request with Bitcoin Lightning — no API key or signup needed. Requires create_payment with toolName='generate_image'.

Inputs: paymentId (required), prompt (required), modelId, imageBase64.

generate_musicAInspect

Generate full songs (up to 6 min) with natural AI vocals, BPM/key control (99%+ accuracy), and 14+ section tags for precise arrangement. Uses Music-2.6 — orchestral and traditional instruments, style-aware mixing. Specify BPM, key, genre, mood in prompt. Returns MP3 URL. 300 sats per song. Pay per request with Bitcoin Lightning — no API key or signup needed. Requires create_payment with toolName='generate_music'.

Inputs: paymentId (required), prompt (required), modelId, lyrics, +5 more.

generate_textAInspect

Generate text using frontier AI language models. Pure per-character pricing (no minimum): Kimi K2.5 (id=6, best, 100 chars/sat, 262K context, vision support, default), GPT-OSS-120B (id=1, better, 333 chars/sat, strong reasoning), Qwen3-32B (id=26, standard, 1000 chars/sat, 119 languages, best value). Supports document Q&A via fileContext and vision analysis via imageBase64 (best model). Stable endpoints — models upgrade automatically. Pay per request with Bitcoin Lightning — no API key or signup needed. Requires create_payment with toolName='generate_text' and the exact prompt.

Inputs: paymentId (required), prompt (required), modelId, systemPrompt, +4 more.

generate_videoAInspect

Generate a video from a text prompt. Uses Kling v3 — cinematic quality, consistent motion, physics-aware rendering. Standard and pro quality modes with optional AI-generated audio track. Async — returns requestId, poll with check_job_status. Pricing: standard 300-400 sats/sec, pro 450-550 sats/sec (audio adds 100 sats/sec). Duration 3-15 seconds. Pay per request with Bitcoin Lightning — no API key or signup needed. Requires create_payment with toolName='generate_video' and duration, mode, generate_audio params.

Inputs: paymentId (required), prompt (required), duration (required), modelId, +2 more.

get_cost_estimateAInspect

Get an exact sat cost quote for a service BEFORE creating a payment. Useful for budget-aware agents to price-check before committing. No payment required, no side effects. Pass service=text-to-speech&chars=1500, service=translate&chars=800, service=transcribe-audio&minutes=5, etc. Returns { amount_sats, breakdown, currency }. Omit params to see the full catalog of supported services.

Inputs: service, model, chars, minutes, +2 more.

get_error_codesAInspect

Get the machine-readable catalog of all error codes this API can return (e.g. TIMEOUT, CONTENT_FILTERED, RATE_LIMITED, L402_REFUND_ISSUED, L402_AUTO_ROUTED). Agents should branch on error_code rather than parsing free-text messages. No payment required.

Inputs: no named parameters.

get_job_resultAInspect

Retrieve the final output of a completed async job. Call ONLY after check_job_status returns status='completed' — calling on a non-completed job returns an error. Returns JSON whose shape depends on jobType: video/video-image → { videoUrl, duration }; image-3d → { modelUrl } (GLB format); transcription → { text, language, segments }; epub-audiobook → { audioUrl, chapters }; ai-call → { transcript, duration, summary }. All URLs are temporary (valid ~1 hour) — download immediately. This tool is free and does not require payment. Do NOT use for synchronous tools — those return results directly.

Inputs: requestId (required), jobType (required).

get_model_pricingAInspect

Get pricing for a specific model by ID. No payment required.

Inputs: modelId (required).

list_modelsAInspect

Discover available AI models with numeric IDs, tier labels, capabilities, and per-call pricing in sats. Call this before create_payment to find the right modelId for your task. Returns JSON array: [{ id, name, tier, description, price, isDefault, category }]. Models marked isDefault=true are used when you omit modelId from create_payment. Filter by category to narrow results to a specific tool. This tool is free, requires no payment, and is idempotent — safe to call repeatedly.

Inputs: category.

list_planned_servicesAInspect

List all planned services with current vote counts. Returns JSON array: [{ slug, name, description, votes }], sorted by votes descending. No payment required — this is a free discovery tool. Use the slug values with vote_on_service to cast votes. This tool is idempotent and safe to call repeatedly.

Inputs: no named parameters.

merge_pdfsAInspect

Merge multiple PDF files into a single document. Preserves bookmarks, links, and formatting. Returns JSON: { url } — a temporary download URL (valid ~1 hour). Minimum 2 files, no maximum. Files are concatenated in array order. 100 sats per merge regardless of file count. Use convert_file instead if you need format conversion (e.g., DOCX→PDF). Pay per request with Bitcoin Lightning — no API key, no account needed. Requires create_payment with toolName='merge_pdfs'.

Inputs: paymentId (required), files (required).

open_voice_bridgeAInspect

Open a Voice Bridge session: a live phone call where YOUR LLM is the brain. Sats4AI provides PSTN + streaming STT + TTS as composable primitives. You decide when to speak (call voice_bridge_say), you read transcripts as they arrive (call poll_voice_bridge), you close the call when done (call end_voice_bridge). Unused deposit time is refunded via LNURL-withdraw. Use this when you want to keep your conversation context private and drive each turn yourself. When NOT to use: not for fully-managed agent-style calls where we handle the brain (use ai_call). Not for one-shot TTS broadcasts or IVR playback (use place_call). Not when live transcript polling adds no value — the per-turn overhead isn't worth it. Privacy: transcripts held in memory only, garbage-collected 30 minutes after the call ends; call audio is never persisted. Pay with Bitcoin Lightning — no telecom account, no signup. Requires create_payment with toolName='voice_bridge_open', phoneNumber, durationMinutes. Deposit: ~10 sats/min US, ~30 intl, ~80 rare.

Inputs: paymentId (required), phoneNumber (required), language, durationMinutes, +4 more.

place_callAInspect

Bridge the digital-physical gap — place an automated phone call to deliver a spoken message or play audio to any number. Useful when your task requires notifying a human, delivering alerts, or reaching someone who isn't online. Pay with Bitcoin Lightning — no telecom account, no KYC, no subscription. Requires create_payment with toolName='place_call' and phoneNumber.

Inputs: paymentId (required), phoneNumber (required), message, audioUrl, +1 more.

poll_voice_bridgeAInspect

Fetch new transcript events from an open Voice Bridge call since the last cursor. Returns partial + final transcripts + system events. Agent should poll in a loop (~500ms-1s). No additional payment.

Inputs: sessionId (required), cursor.

receive_faxAInspect

When you're expecting a fax back — bank confirmation, court filing, signed document — open a 24h receive window at our shared number +1 320 299 1523. Matched by caller ID (last 10 digits of the sender), delivered to your email as soon as it arrives. Optional OCR add-on (+200 sats) returns a searchable text file alongside the PDF — useful for feeding the content to an agent or archiving. Optional callback_url POSTs an HMAC-signed webhook on delivery so your agent doesn't have to poll. No refund if no fax arrives within the window (prevents subscription squatting). If OCR fails, an LNURL-withdraw for 200 sats is included in the delivery email for partial refund. Pay with Bitcoin Lightning — no dedicated fax number rental, no monthly subscription, no account.

Inputs: paymentId (required), email (required), fromNumber (required), ocr, +2 more.

remove_backgroundAInspect

Remove background from any image, returning transparent PNG. Uses BiRefNet (state-of-the-art, Papers with Code — Sm 0.901 on DIS5K). Handles hair, fur, glass, transparency, and complex edges. Stable endpoint — model upgrades automatically as SOTA evolves. 5 sats per image, pay per request with Bitcoin Lightning — no API key or signup needed. Requires create_payment with toolName='remove_background'.

Inputs: paymentId (required), imageBase64 (required).

remove_objectAInspect

Remove unwanted objects from images by describing what to remove — no mask needed. Combines Grounding DINO detection (ECCV 2024) with Bria Eraser inpainting. Just say 'person', 'car', or 'watermark' and the object is erased and filled convincingly. 15 sats per image, pay per request with Bitcoin Lightning — no API key or signup needed. Requires create_payment with toolName='remove_object'.

Inputs: paymentId (required), imageBase64 (required), query (required), box_threshold, +1 more.

request_refundAInspect

Open a MANUAL 48-hour refund review ticket for a service that FAILED (error, timeout, wrong output). Sends an email to the operator. DO NOT call this for unused-minute refunds on metered services (ai_call, voice_bridge) — those are returned automatically as an LNURL-withdraw link in the service's own response under refund.lnurl_withdraw, no manual ticket needed. If you call this on a metered payment that already has a pending LNURL refund, this tool will detect it and return the existing LNURL instead of creating a duplicate ticket.

Inputs: paymentId (required), invoice (required), email, feedback.

restore_faceAInspect

Restore blurry, damaged, or AI-generated faces to sharp, natural quality. Uses CodeFormer (NeurIPS 2022, state-of-the-art FID 32.65 on CelebA-Test). Adjustable fidelity — balance between quality enhancement and identity preservation. Also enhances background and upsamples. Stable endpoint — model upgrades automatically as SOTA evolves. 5 sats per image, pay per request with Bitcoin Lightning — no API key or signup needed. Requires create_payment with toolName='restore_face'.

Inputs: paymentId (required), imageBase64 (required), fidelity, background_enhance, +2 more.

send_emailAInspect

Reach anyone with an email address — useful when your task requires formal communication, sending reports, or contacting someone outside chat. No SMTP server, no domain verification needed. Plain text, max 10,000 chars body, 200 chars subject. 200 sats. Pay with Bitcoin Lightning — no API key or signup needed. Requires create_payment with toolName='send_email'.

Inputs: paymentId (required), to (required), subject (required), body (required), +1 more.

send_faxAInspect

When your task requires a paper-trail on the other end — loan paperwork to a bank, signed contract to a notary, booking confirmation to a hotel in Japan — send a fax to any number worldwide. Two modes: 'pdf' (fetch from public URL) or 'text' (we format typed text into a PDF locally). Optional cover page. Pricing: 500 sats for up to 10 pages, +50 sats per additional page. Max 350 pages / 50 MB. Pass 'pages' to create_payment as 'quantity' to get the right invoice. Pay with Bitcoin Lightning — no fax machine, no phone line, no telecom account.

Inputs: paymentId (required), phoneNumber (required), mode (required), pdfUrl, +3 more.

send_smsAInspect

Reach a human via SMS when your task requires real-world coordination. Send to any phone number worldwide — messages delivered in seconds. No phone plan, no SIM card, no telecom account needed. Pay with Bitcoin Lightning — no API key, no KYC, no subscription. Requires create_payment with toolName='send_sms' and phoneNumber+message at payment time. The phoneNumber and message must match those used in create_payment.

Inputs: paymentId (required), phoneNumber (required), message (required).

text_to_speechAInspect

Text-to-speech with 3 tiers: OmniVoice Global (602+ languages including Yoruba, Bengali, Cebuano, Twi, zero-shot voice cloning, 100 chars/sat — use 'language' parameter with ISO code), Inworld Premium (#1 ranked TTS ELO 1217, emotion control, 40+ languages, 50 chars/sat), Minimax Studio (voice cloning from reference clip, 40+ languages, 10 chars/sat). Adjustable speed (0.5-2.0x). Returns audio URL. Pay with Bitcoin Lightning — no API key or signup needed. When NOT to use: not for phone calls (use place_call for one-shot broadcasts, ai_call for AI voice agents, or open_voice_bridge to drive the call with your own LLM). For rare/underserved languages (Yoruba, Twi, Marathi, Cebuano, etc.), pick OmniVoice Global via language= — Inworld/Minimax don't cover these. Requires create_payment with toolName='text_to_speech'.

Inputs: paymentId (required), text (required), modelId, voice, +3 more.

transcribe_audioAInspect

Transcribe audio to text with timestamps. Uses Mistral Transcription — high-accuracy speech recognition that handles accents, background noise, and overlapping speakers. 13 languages: en, zh, hi, es, ar, fr, pt, ru, de, ja, ko, it, nl. Up to 512 MB / 3 hours per file. Async — returns requestId, poll with check_job_status(jobType='transcription'), then get_job_result. 10 sats/min. Privacy: audio and transcripts are ephemeral — processed, returned, and discarded. Never persisted. Pay per request with Bitcoin Lightning — no API key or signup needed. Requires create_payment with toolName='transcribe_audio'.

Inputs: paymentId (required), audioBase64 (required), language.

transcribe_translateAInspect

Compound endpoint — one payment turns audio in any of 13 source languages into both a transcript AND a translation in any of 119 target languages. Perfect for WhatsApp voice messages in a language you don't speak (Yoruba → English), or recording a meeting in another language and reading it in yours. Auto-detects source if omitted. Async — returns requestId, poll with check_job_status(jobType='transcribe-translate'). Flat price covers STT + translation. Cheaper than calling transcribe_audio + translate_text separately for typical voice messages. Pay with Bitcoin Lightning — no API key or signup needed. Requires create_payment with toolName='transcribe_translate'.

Inputs: paymentId (required), audioBase64 (required), targetLanguage (required), sourceLanguage.

translate_textAInspect

Translate text across 119 languages with high accuracy. Uses Qwen3-32B — multilingual transformer with strong low-resource language support. Auto-detects source language. Privacy-preserving: no data stored. Pricing: 1 sat per 1,000 characters, minimum 1 sat per request. Language parameters accept English names ('Spanish', 'Chinese (Simplified)') or ISO-639 codes / locale tags ('es', 'en-US', 'pt-BR', 'zh-Hans'). Supported languages: Afrikaans, Albanian, Amharic, Arabic, Armenian, Assamese, Azerbaijani, Basque, Belarusian, Bengali, Bosnian, Bulgarian, Burmese, Catalan, Cebuano, Chichewa, Chinese (Simplified), Chinese (Traditional), Corsican, Croatian, Czech, Danish, Dari, Dutch, English, Esperanto, Estonian, Farsi, Fijian, Filipino, Finnish, French, Frisian, Galician, Georgian, German, Greek, Guarani, Gujarati, Haitian Creole, Hausa, Hawaiian, Hebrew, Hindi, Hmong, Hungarian, Icelandic, Igbo, Indonesian, Irish, Italian, Japanese, Javanese, Kannada, Kazakh, Khmer, Kinyarwanda, Korean, Kurdish, Kyrgyz, Lao, Latvian, Lingala, Lithuanian, Luganda, Luxembourgish, Macedonian, Malagasy, Malay, Malayalam, Maltese, Maori, Marathi, Mongolian, Nepali, Norwegian, Occitan, Odia, Pashto, Polish, Portuguese, Punjabi, Romanian, Romansh, Russian, Samoan, Scots Gaelic, Serbian, Sesotho, Setswana, Shona, Sindhi, Sinhala, Slovak, Slovenian, Somali, Spanish, Sundanese, Swahili, Swedish, Tajik, Tamil, Tatar, Telugu, Thai, Tigrinya, Tongan, Turkish, Turkmen, Ukrainian, Urdu, Uzbek, Vietnamese, Welsh, Wolof, Xhosa, Yiddish, Yoruba, Zulu. Pay per request with Bitcoin Lightning — no API key or signup needed. Requires create_payment with toolName='translate_text' and prompt (the text to translate).

Inputs: paymentId (required), text (required), targetLanguage (required), sourceLanguage, +1 more.

upscale_imageAInspect

Upscale images 2x or 4x with neural super-resolution. Uses Real-ESRGAN (ICCV 2021, PSNR 32.73dB on Set5 4x, 100M+ production runs). Recovers real detail from low-resolution images — not interpolation. Optional face enhancement. Stable endpoint — model upgrades automatically as SOTA evolves. 5 sats per image, pay per request with Bitcoin Lightning — no API key or signup needed. Requires create_payment with toolName='upscale_image'.

Inputs: paymentId (required), imageBase64 (required), scale, face_enhance.

voice_bridge_sayAInspect

Inject audio into an open Voice Bridge call. Two modes: (1) text — we synthesize via OmniVoice TTS in any of 602 languages; (2) audio_base64 + encoding — bring your own audio (mulaw_8000 or pcm_l16_16000 for MVP). STT is automatically muted while we inject, so the agent doesn't hear itself. No additional payment — covered by the session deposit.

Inputs: sessionId (required), text, language, voiceDescription, +2 more.

vote_on_serviceAInspect

Vote for a planned service to be built next. Returns JSON: { success, slug, newVoteCount }. 1 sat per vote — multiple votes allowed. Call list_planned_services first to discover valid slugs and current vote counts. Highest-voted services get prioritized. Requires create_payment with toolName='vote_on_service'.

Inputs: paymentId (required), slug (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.1/5.0

    Scored across 49 tools

    Disambiguation5/5

    Each tool targets a distinct action or domain, with detailed descriptions that clearly differentiate even related tools (e.g., ai_call vs. open_voice_bridge vs. place_call). No two tools have ambiguous or overlapping purposes.

    Naming Consistency5/5

    All tool names follow a consistent snake_case verb_noun pattern (e.g., generate_image, extract_document, send_sms). No mixing of conventions, making the set predictable and easy for agents to navigate.

    Tool Count4/5

    At 49 tools, the count is high but appropriate for the broad scope of the server, which covers voice, video, image, document, and communication services. Each tool earns its place, though the size may feel heavy for narrower use cases.

    Completeness4/5

    The tool set covers a wide range of common AI tasks and includes necessary infrastructure (payment, job status, error codes). Minor gaps exist (e.g., no tool for bulk operations or advanced audio editing), but the surface is mostly complete for the intended domain.

    Maintenance

    ActivityActive
    ResponsivenessLimited data

    Related MCP Connectors

    Related MCP Servers

    Appeared in Searches