# Private AI Media Generation (remote · livepairai.com)

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

- Trust score: 77/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-17

## Components

- remote · `livepairai.com`: 77/100 (this document), [markdown](https://verifymcp.io/servers/com-livepairai-livepair-hub/livepairai.md), [page](https://verifymcp.io/servers/com-livepairai-livepair-hub/livepairai)

## Channel facts

- Endpoint: `https://livepairai.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.1`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-17.

- **Endpoint Security**: 74/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 83/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 2896 tokens (~107/item across 27 items; 14 tools + 13 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 33/100
  - Stability observed for 10 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 98/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 95% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 14 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 16 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Private AI Media Generation MCP server?

Private AI Media Generation is a hosted endpoint at https://livepairai.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http com-livepairai-livepair-hub 'https://livepairai.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-livepairai-livepair-hub": {
      "url": "https://livepairai.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-livepairai-livepair-hub": {
      "type": "http",
      "url": "https://livepairai.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-livepairai-livepair-hub]
url = "https://livepairai.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-livepairai-livepair-hub": {
      "type": "remote",
      "url": "https://livepairai.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-livepairai-livepair-hub --url 'https://livepairai.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-livepairai-livepair-hub:
    url: "https://livepairai.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-livepairai-livepair-hub": {
      "Transport": "http",
      "Url": "https://livepairai.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-livepairai-livepair-hub -t streamable-http -u 'https://livepairai.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-livepairai-livepair-hub": {
      "type": "http",
      "url": "https://livepairai.com/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-16 (score 77, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [functional regression] Schema quality: pass → fail
- [functional] New tool “list_reference_packs”
- [functional] New tool “search_references”
- [cosmetic] “generate_image” added an optional parameter “referenceIds”
- [cosmetic] “generate_image” added an optional parameter “useReferences”

### 2026-10-15 (score 76, 0)

- [security] Tool “generate_image” rewrote its description, which is the text the model reads
- [cosmetic] “generate_image” added an optional parameter “extra”
- [cosmetic] “generate_image” added an optional parameter “image2”
- [cosmetic] “generate_image” added an optional parameter “video”

### 2026-10-14 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-12 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 17. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-10 (score 74, +6)

- [security improvement] HTTPS: unverified → pass
- [security] The server rewrote its instructions, which are the text every model session reads
- [security] The server changed its declared name: livepair → private-media-generation
- [security] Tool “enhance_prompt” rewrote its description, which is the text the model reads
- [security] Tool “generate_image” rewrote its description, which is the text the model reads
- [security] Tool “list_models” rewrote its description, which is the text the model reads
- [security] Tool “search_prompts” rewrote its description, which is the text the model reads
- [functional regression] Tool coverage: 100% → 93%
- [functional improvement] Schema quality: 112 → 91
- [functional improvement] Stability: unverified → 0.10
- [functional] The server now declares the “prompts” capability
- [functional] The server now declares the “resources” capability
- [functional] First check of Schema quality: 100
- [functional] Schema quality: excellent → good
- [functional] New prompt “find_prompt”
- [functional] New prompt “generate_media”
- [functional] New prompt “private_animation”
- [functional] New resource “abstract prompt pack”
- [functional] New resource “anime prompt pack”
- [functional] New resource “architecture prompt pack”
- [functional] New resource “character prompt pack”
- [functional] New resource “docs”
- [functional] New resource “fantasy prompt pack”
- [functional] New resource “food prompt pack”
- [functional] New resource “landscape prompt pack”
- [functional] New resource “manifest”
- [functional] New resource “models”
- [functional] New resource “portrait prompt pack”
- [functional] New resource “product prompt pack”
- [functional] New resource “sci-fi prompt pack”
- [functional] New tool “chat_text”
- [functional] New tool “get_balance”
- [functional] New tool “get_job”
- [functional] New tool “get_pack”
- [functional] New tool “quote_price”
- [functional] New tool “recommend_model”
- [cosmetic] “enhance_prompt” added an optional parameter “mode”
- [cosmetic] “generate_image” added an optional parameter “payer”
- [cosmetic] “generate_image” reworded the description of “image”
- [cosmetic] “generate_image” reworded the description of “prompt”
- [cosmetic] “generate_image” reworded the description of “resolution”
- [cosmetic] “generate_image” made “prompt” optional
- [cosmetic] Tool “generate_image” changed its title: Generate an image or video (paid, x402) → Generate an image or video (paid)

### 2026-10-07 (score 68)

First indexed and scored.

## MCP tools (14)

### `search_prompts` (~121 tokens)

Search community prompts

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.

Input parameters:

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

### `get_prompt` (~60 tokens)

Get a prompt recipe

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.

Input parameters:

- `id` (string, required): Card id from search_prompts or trending_prompts

### `trending_prompts` (~60 tokens)

Trending prompts

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.

Input parameters:

- `limit` (integer): Max results (default 10)

### `enhance_prompt` (~79 tokens)

Improve a generation prompt

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.

Input parameters:

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

### `generate_image` (~555 tokens)

Generate an image or video (paid)

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.

Input parameters:

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

### `chat_text` (~182 tokens)

Private LLM text completion (paid)

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.

Input parameters:

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

### `get_job` (~47 tokens)

Poll a generation job

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

Input parameters:

- `jobId` (string, required): jobId returned by the generate endpoint

### `get_balance` (~37 tokens)

Check prepaid credit balance

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

### `quote_price` (~134 tokens)

Quote a generation price

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.

Input parameters:

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

### `search_references` (~179 tokens)

Search media references

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.

Input parameters:

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

### `list_reference_packs` (~72 tokens)

List curated reference packs

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.

### `recommend_model` (~147 tokens)

Pick a model for a task

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).

Input parameters:

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

### `get_pack` (~98 tokens)

Prompt pack by topic

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.

Input parameters:

- `limit` (integer)
- `topic` (string, required): Topic tag, e.g. anime, product, portrait

### `list_models` (~67 tokens)

List generation models

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).

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-livepairai-livepair-hub/livepairai#diagnostics

## Score history

- 2026-10-17: 77
- 2026-10-16: 77
- 2026-10-15: 76
- 2026-10-14: 76
- 2026-10-13: 75
- 2026-10-12: 75
- 2026-10-10: 74
- 2026-10-07: 68

## Common questions

### What is the Private AI Media Generation MCP server?

Private AI Media Generation is an MCP server listed in the public MCP registry as com.livepairai/livepair-hub. Paid AI image/video generation for agents, x402 USDC or API key, no account needed. This page covers its hosted endpoint (https://livepairai.com/mcp).

### Is the Private AI Media Generation MCP server safe to use?

Private AI Media Generation scores 77 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Private AI Media Generation MCP server expose?

Private AI Media Generation exposes 14 tools: search_prompts, get_prompt, trending_prompts, enhance_prompt, generate_image, and 9 more. Their descriptions and schemas cost roughly 1,838 tokens of context every time the server is loaded.

### Does the Private AI Media Generation MCP server require authentication?

No. We connected to Private AI Media Generation without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Private AI Media Generation MCP server still maintained?

Private AI Media Generation is still listed as active in the MCP registry. We last reached this channel on 17 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://livepairai.com/mcp
- Website: https://livepairai.com/
- Changelog RSS feed: https://verifymcp.io/servers/com-livepairai-livepair-hub/livepairai.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-livepairai-livepair-hub/livepairai.json
- HTML version of this page: https://verifymcp.io/servers/com-livepairai-livepair-hub/livepairai