com.livepairai/livepair-hub

Est-ce que com.livepairai/livepair-hub est sûr ?

Au dernier audit MCP Hub, le serveur MCP « com.livepairai/livepair-hub » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Les 14 outils

• chat_text≈ 303 tokens

  OpenAI-compatible chat completions — frontier and open-weight models (list under textModels in GET /v1/agent/models). PAID. If this MCP request carries your API key (x-api-key / Bearer lp_…) the completion executes right here and returns {choices, usage}; without a key the upstream answers 402 and this tool returns the x402 payment requirements. Price = estimated input tokens × input rate + max_tokens × output rate — set max_tokens tight to bill tight. Metering keeps token counts only.

  Paramètres, retour & exemple (4)

  Paramètres

  • model · string · optionnel
    Text model id (see textModels in list_models)
  • payer · string · optionnel
    Your 0x… wallet — volume-tier discount (x402 rail)
  • prompt · string · requis
    The text request — your user message
  • maxTokens · number · optionnel
    Output cap, billed at this amount

  Exemple d'appel

  {"name": "chat_text", "arguments": {"prompt": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• enhance_prompt≈ 188 tokens

  Rewrite a rough prompt idea into the structured form our image models follow best (subject, composition, style, negatives). Use before generate_image — better input, better output.

  Paramètres, retour & exemple (2)

  Paramètres

  • mode · string · optionnel · t2i | i2i | t2v | i2v
    Target mode — pass the model's mode so the rewrite matches (default t2i)
  • prompt · string · requis
    The raw prompt idea to improve

  Exemple d'appel

  {"name": "enhance_prompt", "arguments": {"prompt": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• generate_image≈ 754 tokens

  Render or transform an image or video with a catalog model (t2i, i2i, t2v, i2v, tool — tools like upscale/remove-background take image with no prompt; face-swap takes image + image2; motion models take image + video) — including the private model line flagged private=true in list_models. PAID. If this MCP request carries your API key (x-api-key / Authorization: Bearer lp_… — create at https://livepairai.com/settings after /auth/sign-up) the run executes right here and returns {status:'done',url} or a jobId to poll with get_job. Without a key the upstream answers 402 and this tool returns the x402 payment requirements (USDC on Base) for your wallet to settle.

  Paramètres, retour & exemple (11)

  Paramètres

  • extra · object · optionnel
    Model-specific settings keyed by the names in the model's `extraSettings` (list_models) — e.g. {quality:'720p'} for pixverse-motion, {targetGender:'female'} for face swaps
  • image · string · optionnel
    Source image — required for i2i/i2v/tool models. Public http(s) URL or data:image URI. Use AI-generated or owned images only — never real-person photos without consent
  • payer · string · optionnel
    Your 0x… wallet — applies your volume-tier discount; must equal the wallet signing the payment (x402 rail)
  • video · string · optionnel
    Source clip — required for motion-control and video-face-swap models (motion reference or swap target). https URL or data:video URI, ≤40MB. Priced on the clip's measured length
  • image2 · string · optionnel
    Second image input — the face to place on face-swap models (image-face-swap, video-face-swap). Same URL/data:image rules; use only faces you have consent to use
  • prompt · string · optionnel
    The prompt to render — call enhance_prompt first for best results. Not needed for mode=tool models (upscale, remove-bg) — the image is the request
  • modelId · string · optionnel
    Model id from list_models (default: fastest t2i)
  • duration · number · optionnel
    Video length in seconds (video models)
  • resolution · string · optionnel
    Video resolution tier, or upscale tier for tool models
  • referenceIds · array · optionnel
    Pin media references from search_references (yours or pack refs, ≤4) — fills the model's open image/video inputs as style/content references
  • useReferences · boolean · optionnel
    Auto-pick refs from your library by prompt semantics (owner namespace only) — prefer search_references + referenceIds so the user can approve candidates

  Exemple d'appel

  {"name": "generate_image", "arguments": {"extra": {}, "image": "texte", "payer": "texte", "video": "texte", "image2": "texte", "prompt": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_balance≈ 105 tokens

  Prepaid credit balance and recent ledger for the API key on this MCP request — needs an lp_ key (x-api-key / Bearer).

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "get_balance", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_job≈ 134 tokens

  Check a running job returned by generate_image — free. Returns {status:'done',url} | running | failed.

  Paramètres, retour & exemple (1)

  Paramètres

  • jobId · string · requis
    jobId returned by the generate endpoint

  Exemple d'appel

  {"name": "get_job", "arguments": {"jobId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_pack≈ 196 tokens

  A themed bundle of curated prompt picks (themes: anime, portrait, landscape, product, character, sci-fi, fantasy, abstract, food, architecture). Curated packs are rebuilt daily and carry real paid-run counts — prompts that already produced paid results. Falls back to a live topic search when no pack covers the theme.

  Paramètres, retour & exemple (2)

  Paramètres

  • limit · integer · optionnel
  • topic · string · requis
    Topic tag, e.g. anime, product, portrait

  Exemple d'appel

  {"name": "get_pack", "arguments": {"topic": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_prompt≈ 140 tokens

  Fetch one community prompt card by id — the verbatim prompt, model it ran on, the result media, like/view counts, and a studio link that preloads it.

  Paramètres, retour & exemple (1)

  Paramètres

  • id · string · requis
    Card id from search_prompts or trending_prompts

  Exemple d'appel

  {"name": "get_prompt", "arguments": {"id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• list_models≈ 133 tokens

  List the public image and video generation catalog — id, label, mode (text-to-image, image-to-video, etc), rough generation time, and private flag (private AI models — i2i/i2v source images must be AI-generated or owned, no real-person photos without consent).

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "list_models", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• list_reference_packs≈ 142 tokens

  Curated moodboards usable as generation references — each pack is a cohesive look (lighting/grade/mood: golden-hour, neon-night, noir-bw…). Read-shared for everyone; pick one for the user's intent, search inside it via search_references(pack), then pin chosen refs via referenceIds.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "list_reference_packs", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• quote_price≈ 250 tokens

  Exact USDC price for a model+settings combo before paying — images are flat per call, video is per-second × duration at the resolution tier. The x402 endpoint always re-quotes from the body, so this is the same number it would charge.

  Paramètres, retour & exemple (6)

  Paramètres

  • payer · string · optionnel
    Your 0x… payer wallet — applies your volume-tier discount
  • modelId · string · requis
    Model id from list_models
  • duration · number · optionnel
    Video seconds (video models)
  • imageSize · string · optionnel
    Image size label
  • resolution · string · optionnel
    Video resolution tier
  • aspectRatio · string · optionnel

  Exemple d'appel

  {"name": "quote_price", "arguments": {"modelId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• recommend_model≈ 276 tokens

  Decide which model fits a need — returns the modelId to use with generate_image. Cheapest, fastest, or highest quality; for images, video, or utility tools (upscale, background removal); with or without a source image. Pass private:true to restrict to the private AI model line (i2v models).

  Paramètres, retour & exemple (4)

  Paramètres

  • goal · string · requis · cheapest | fastest | best_quality
    What to optimize for
  • media · string · requis · image | video | tool
    Output type — 'tool' = image transforms (upscale, remove-bg)
  • private · boolean · optionnel
    True to consider only the private AI model line
  • hasSourceImage · boolean · optionnel
    True when a source image drives the job (forces i2i/i2v/tool)

  Exemple d'appel

  {"name": "recommend_model", "arguments": {"goal": "cheapest", "media": "image"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• search_prompts≈ 240 tokens

  Keyword search over the community prompt library — tested AI image and video prompts with the results they produced. Use for style/subject/model lookups. For trending or most-used prompts call trending_prompts instead. Returns prompt text, model, result media, and a link to run it.

  Paramètres, retour & exemple (3)

  Paramètres

  • kind · string · optionnel · image | video | agent
    Optional media type filter
  • limit · integer · optionnel
    Max results (default 8)
  • query · string · requis
    What to look for — style, subject, or model name (e.g. 'cinematic portrait', 'anime pose')

  Exemple d'appel

  {"name": "search_prompts", "arguments": {"query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• search_references≈ 298 tokens

  Semantic search over your media-reference library AND shared curated moodboards — describe the look you want ('warm golden diner', 'neon night street') and get candidate images/clips with preview urls to show the user. Pass 'pack' to search inside one moodboard picked from list_reference_packs. With your lp_ key on this request your own uploaded refs are included; without it only the curated packs are searched. This tool never attaches: discuss candidates with the user, then pin chosen ids via referenceIds on generate_image.

  Paramètres, retour & exemple (3)

  Paramètres

  • k · number · optionnel
    Max candidates (default 8, max 20)
  • pack · string · optionnel
    Scope search to one moodboard slug from list_reference_packs (e.g. 'neon-night')
  • query · string · requis
    Describe the look/mood/style — matched semantically against reference media

  Exemple d'appel

  {"name": "search_references", "arguments": {"query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• trending_prompts≈ 149 tokens

  Use when the user asks for trending, most-used, most popular, or top prompts — do NOT keyword-search for these. Returns community prompt cards ranked by the paid generations they actually drove.

  Paramètres, retour & exemple (1)

  Paramètres

  • limit · integer · optionnel
    Max results (default 10)

  Exemple d'appel

  {"name": "trending_prompts", "arguments": {"limit": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

https://livepairai.com/mcp