Bitcoin-powered AI tools via MCP + Lightning Network micropayments (L402)
Bitcoin-powered AI tools via MCP + Lightning Network micropayments (L402)
active Production-safe Score 95/100 http no auth
At a glance
| Endpoint | https://sats4ai.com/api/mcp |
|---|---|
| Source | https://github.com/cnghockey/sats4ai-mcp-server |
| Transport | http |
| Tools | 58 |
| Auth | none |
| First seen | 2026-03-16 10:44:38 |
| Last checked | 2026-11-17 21:56:08 |
Observed reliability
| 7-day uptime | 100% |
|---|---|
| 24-hour uptime | 100% |
| Handshake success | 100% |
| Latency p50 / p95 | 330 / 598 ms |
| Last successful check | 2026-11-17 21:56:08 |
Measured by Arclan's validator via repeated live MCP handshakes. How this is computed →
Tools (58)
create_payment— Create a Lightning invoice to pay for one AI service call. Returns JSON: { paymentId, lightningInvoice (BOLT11), amountSats, expiresAt }. Eacreate_cart— Pay for 2 to 10 calls with ONE Lightning invoice, up to 2,000 sats in all. Each item is { toolName, ...the same inputs create_payment takescheck_payment_status— Check whether a Lightning invoice has been paid. Returns JSON: { paid, serviceUsed, refundAllowed, readyToUse, next, state } — readyToUse=trgenerate_image— Generate an image from a text prompt. Returns JSON with image URL. Models: Grok Imagine 2 (fast creative generation, 100 sats), Seedream 5 Pgenerate_video— Generate cinematic video from a text prompt. Uses MiniMax H3 — top 2 on the Artificial Analysis text-to-video leaderboard — with native audianimate_image— Animate a still image into cinematic video with MiniMax H3 — provide a first frame and a prompt to direct the motion. Native audio. Async —check_job_status— Poll the status of an async job. Use this after calling any async tool (generate_video, animate_image, generate_3d_model, transcribe_audio,get_job_result— Retrieve the final output of a completed async job. Call ONLY after check_job_status returns status='COMPLETED' — calling on a job that hasawait_result— Wait for an async job to finish and return its result in ONE call — no manual polling loop. Pass the requestId + jobType from an async toolanalyze_image— Analyze and describe image content, answer visual questions, extract information from screenshots or photos. Uses Qwen VL — multimodal visiogenerate_text— Generate text using frontier AI language models. Pure per-character pricing (no minimum): Kimi K3 (best, ~10 chars/sat, 1M context, default)generate_music— Generate a full song with AI vocals from a style prompt plus lyrics — or an INSTRUMENTAL bed / underscore (background music under video narrtext_to_speech— Text-to-speech with 3 tiers: OmniVoice Global (602+ languages including Yoruba, Bengali, Cebuano, Twi, voice design, ~106 chars/sat — use 'ltranscribe_audio— Transcribe audio to text with WORD-LEVEL timestamps (timestamps:'word' returns per-word start/end times — subtitle alignment, karaoke captiotranscribe_translate— Compound endpoint — one payment turns audio in any of 13 source languages into both a transcript AND a translation in any of 119 target langtranslate_epub— Translate a whole EPUB into another language and get an EPUB back. Every chapter is translated with its markup intact — headings, emphasis,generate_3d_model— Generate a textured 3D GLB model from EITHER a photo OR a text prompt (provide exactly one, not both). Uses Tencent Hunyuan3D — high-fidelitextract_document— Extract text from PDFs and images as clean Markdown. Uses Mistral OCR — handles complex layouts, tables, handwriting, multi-column documentsconvert_file— Convert files between 200+ formats: documents (PDF, DOCX, XLSX, HTML→PDF), images (PNG, JPG, WEBP, SVG), PDF first page to image (PDF→JPG, Psend_email— Reach anyone with an email address — useful when your task requires formal communication, sending reports, or contacting someone outside chaclone_voice— Clone a voice you own or have permission to use, from a single audio sample. Returns a reusable voice_id for text_to_speech. Requires consenedit_image— Edit an image with natural language instructions. Uses MAI-Image-2.6, ranked #3 on the Artificial Analysis image-editing leaderboard as of Smerge_pdfs— Merge multiple PDF files into a single document. Preserves bookmarks, links, and formatting. Returns JSON: { url } — a temporary download URconvert_html_to_pdf— Convert HTML or Markdown to a pixel-perfect PDF. Returns JSON: { url } — a temporary download URL (valid ~1 hour). Great for generating invorender_card— Render a typographic card — headline, versus (two columns), list, stat (one big number) or quote — as a PNG or JPEG at 1920x1080 or 2560x144translate_text— Translate text across 119 languages with high accuracy. The target language picks the engine: GPT-OSS 120B by default, or a higher-scoring mmultilingual_ask— Ask a frontier AI a question in your OWN language and get the answer back in that same language, in ONE payment. We translate the question ttranslate_rare_language— Translate into 452 languages, 251 of them NOT supported by ChatGPT, Claude or Gemini (29 of those 251 measured at fair quality or better agaextract_receipt— Extract structured data from receipts, invoices, and financial documents. Uses a dual-model pipeline (Mistral OCR + Kimi K3) for high-accuraboardingpass_wallet— Turn airline boarding passes (PDF or screenshot) into Google Wallet passes with the fields a plain scan drops — boarding zone, gate, boardine_signature— Send a document out for legally binding e-signature and have the signed copy emailed back. Upload the PDF, name up to 3 signers, and give thepub_to_audiobook— Convert books (EPUB/PDF/TXT) to full audiobooks with automatic chapter detection, multi-voice narration, and optional translation to any lansend_sms— Reach a human via SMS when your task requires real-world coordination. Sends to 190+ countries; delivery timing varies by destination. Refusplace_call— Bridge the digital-physical gap — place an automated phone call to deliver a spoken message or play audio to any number. Useful when your tasend_fax— 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 horeceive_fax— When you're expecting a fax back — bank confirmation, court filing, signed document — open a 24h receive window at our shared number +1 320ai_call— When your task hits a wall that requires a human — booking, negotiating, navigating IVR menus, getting information from a business — send anconfirm_ai_call— Confirm an AI call after reviewing push-back questions, optionally providing answers to missing info. Required when ai_call returns state='popen_voice_bridge— Open a phone call you drive one turn at a time: we dial, transcribe what the other side says, and speak whatever text you send. You call voivoice_bridge_say— Inject audio into an open Voice Bridge call. Two modes: (1) text — we synthesize speech in any of 602 languages (English, Spanish and Germanpoll_voice_bridge— Fetch new transcript events from an open Voice Bridge call since the last cursor. Returns partial + final transcripts + system events. Passend_voice_bridge— Hang up a Voice Bridge call, finalize billing, and return a LNURL-withdraw refund link for unused deposit time. Also returns the final translist_models— Discover available AI models with numeric IDs, tier labels, capabilities, and per-call pricing in sats. Call this before create_payment to fget_model_pricing— Get pricing for a specific model by ID. No payment required.get_cost_estimate— Get an exact sat cost quote for a service BEFORE creating a payment. Useful for budget-aware agents to price-check before committing. No payget_error_codes— Get the machine-readable catalog of all error codes this API can return (e.g. TIMEOUT, CONTENT_FILTERED, RATE_LIMITED, L402_REFUND_ISSUED, Lrequest_refund— Open a MANUAL 48-hour refund review ticket for a service that FAILED (error, timeout, wrong output). Sends an email to the operator. DO NOTremove_background— Remove background from any image, returning transparent PNG. Uses BiRefNet (state-of-the-art, Papers with Code — Sm 0.901 on DIS5K). Handlesupscale_image— Upscale images 2x or 4x with neural super-resolution. Uses Real-ESRGAN (ICCV 2021, PSNR 32.73dB on Set5 4x, 100M+ production runs). Recoversrestore_face— Restore blurry, damaged, or AI-generated faces to sharp, natural quality. Uses CodeFormer (NeurIPS 2022, state-of-the-art FID 32.65 on Celebestimate_depth— Estimate per-pixel depth from a single photo. Depth Anything V2 (NeurIPS 2024, 3.8M+ runs) returns BOTH the raw greyscale depth map — what adetect_nsfw— Classify image safety (normal / suggestive / explicit). Falcons.ai NSFW detection — 100x cheaper and faster than asking an LLM. Returns clasdetect_objects— Detect and locate objects in an image by name. Grounding DINO (open-set detector, ECCV 2024) — describe what to find in natural language, geremove_object— Remove unwanted objects from images by describing what to remove — no mask needed. Combines Grounding DINO detection (ECCV 2024) with Bria Ecolorize_image— Colorize black-and-white or grayscale photos. DDColor (dual-decoder, ICCV 2023) — vivid, natural colorization. Impossible for text/vision LLdeblur_image— Recover detail from camera-shake and accidental motion blur. NAFNet (ECCV 2022, SOTA on GoPro/SIDD benchmarks). Best for: handheld shake, buvote_on_service— Vote for a planned service to be built next. Returns JSON: { success, slug, newVoteCount }. 1 sat per vote — multiple votes allowed. Call lilist_planned_services— List all planned services with current vote counts. Returns JSON array: [{ slug, name, description, votes }], sorted by votes descending. No
Validation history
| Checked | Reachable | Handshake | Latency | Score | State |
|---|---|---|---|---|---|
| 2026-11-17 21:56:08 | ✓ | ✓ | 270 ms | 94 | active |
| 2026-11-17 21:40:54 | ✓ | ✓ | 279 ms | 94 | active |
| 2026-11-17 21:25:41 | ✓ | ✓ | 279 ms | 94 | active |
| 2026-11-17 21:10:32 | ✓ | ✓ | 430 ms | 91 | active |
| 2026-11-17 20:55:30 | ✓ | ✓ | 269 ms | 94 | active |
| 2026-11-17 20:40:27 | ✓ | ✓ | 396 ms | 91 | active |
| 2026-11-17 20:25:25 | ✓ | ✓ | 412 ms | 91 | active |
| 2026-11-17 20:10:11 | ✓ | ✓ | 382 ms | 91 | active |
| 2026-11-17 19:54:26 | ✓ | ✓ | 371 ms | 91 | active |
| 2026-11-17 19:39:21 | ✓ | ✓ | 396 ms | 91 | active |
| 2026-11-17 19:24:01 | ✓ | ✓ | 359 ms | 91 | active |
| 2026-11-17 19:08:54 | ✓ | ✓ | 273 ms | 94 | active |
| 2026-11-17 18:53:37 | ✓ | ✓ | 440 ms | 91 | active |
| 2026-11-17 18:38:36 | ✓ | ✓ | 438 ms | 91 | active |
| 2026-11-17 18:23:31 | ✓ | ✓ | 462 ms | 91 | active |
Query this programmatically
Agents can pull this record live over the MCP protocol or REST:
get_server("https://sats4ai.com/api/mcp") # via the Arclan MCP endpoint https://arclan.ai/mcp
GET https://arclan.ai/api/registry/sats4ai-com-api-mcp # JSON