Private AI Media Generation

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

Paid AI image/video generation for agents — x402 USDC or API key, no account needed.

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "Private AI Media Generation": {
      "url": "https://livepairai.com/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (14)

• search_prompts read-only

  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.

  Parameters:

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

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• get_prompt read-only

  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.

  Parameters:

  • id (required) — string — Card id from search_prompts or trending_prompts

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• trending_prompts read-only

  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.

  Parameters:

  • limit — integer — Max results (default 10)

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• enhance_prompt read-only

  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.

  Parameters:

  • prompt (required) — string — The raw prompt idea to improve
  • mode — string — Target mode — pass the model's mode so the rewrite matches (default t2i)

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• generate_image

  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.

  Parameters:

  • extra — object — 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 — 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 — Your 0x… wallet — applies your volume-tier discount; must equal the wallet signing the payment (x402 rail)
  • video — string — 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 — 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 — 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 — Model id from list_models (default: fastest t2i)
  • duration — number — Video length in seconds (video models)
  • resolution — string — Video resolution tier, or upscale tier for tool models
  • referenceIds — array — 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 — Auto-pick refs from your library by prompt semantics (owner namespace only) — prefer search_references + referenceIds so the user can approve candidates

  Hints: read-only no · destructive no · idempotent no · open-world no

• chat_text

  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.

  Parameters:

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

  Hints: read-only no · destructive no · idempotent no · open-world no

• get_job

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

  Parameters:

  • jobId (required) — string — jobId returned by the generate endpoint

  Hints: read-only no · destructive no · idempotent yes · open-world no

• get_balance read-only

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

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• quote_price read-only

  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.

  Parameters:

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

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• search_references read-only

  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.

  Parameters:

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

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• list_reference_packs read-only

  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.

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• recommend_model read-only

  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).

  Parameters:

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

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• get_pack read-only

  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.

  Parameters:

  • topic (required) — string — Topic tag, e.g. anime, product, portrait
  • limit — integer

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• list_models read-only

  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).

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

Publisher website

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.