# LivePair MCP server

> Browse a community AI prompt library and generate images or video, paying per call in USDC through x402.

- Listing: https://mcp.tc/i/livepair
- Connect: use the server's own URL `https://livepairai.com/mcp` (no sign-in); clients connect to it directly. The listing link is a page, not an MCP endpoint.
- Type: remote (Streamable HTTP)
- Auth: none
- Category: [AI & Machine Learning](https://mcp.tc/c/ai-ml)
- Vendor: LivePair AI
- Homepage: <https://livepairai.com/>

## About

LivePair gives an assistant access to a community library of tested image and video prompts, with the model used and the result media for each. It can search and rank prompts, fetch themed packs, list models, recommend a model, improve a rough prompt, quote an exact price, and start image or video generation (text-to-image, image-to-image, text-to-video, image-to-video).

The server is hosted at a streamable HTTP endpoint and needs no sign-in or API key for browsing. Generation is paid: the generate call returns an HTTP 402 with x402 payment requirements in USDC on Base, so an x402-capable wallet client is needed to settle it. Slow jobs return a job ID that can be polled for free.

## What it can do

- Search community prompts by style, subject or model
- List trending prompts ranked by paid generations
- Fetch themed prompt packs such as anime, product or sci-fi
- Rewrite a rough idea into a structured generation prompt
- Get an exact USDC price quote before paying
- Generate images or video through a paid x402 endpoint
- Poll generation jobs until the result URL is ready

## Tools (14)

- `search_prompts`: Keyword search over the community prompt library by style, subject or model. (read-only)
- `get_prompt`: Fetch one prompt card by id with verbatim prompt, model, result media and counts. (read-only)
- `trending_prompts`: Return prompt cards ranked by the paid generations they drove. (read-only)
- `enhance_prompt`: Rewrite a rough idea into a structured prompt with subject, composition, style and negatives. (read-only)
- `generate_image`: Paid x402 call that renders an image or video with a LivePair model.
- `chat_text`: OpenAI-compatible chat completions — frontier and open-weight models (list under textModels in GET /v1/agent/models).
- `get_job`: Poll a generation job for done, running or failed status.
- `get_balance`: Prepaid credit balance and recent ledger for the API key on this MCP request — needs an lp\_ key (x-api-key / Bearer). (read-only)
- `quote_price`: Give the exact USDC price for a model and settings combination. (read-only)
- `search_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. (read-only)
- `list_reference_packs`: Curated moodboards usable as generation references — each pack is a cohesive look (lighting/grade/mood: golden-hour, neon-night, noir-bw…). (read-only)
- `recommend_model`: Pick the model ID that fits a goal, media type and source image. (read-only)
- `get_pack`: Return a themed bundle of curated prompts, falling back to topic search. (read-only)
- `list_models`: List public image and video models with id, label, mode and rough generation time. (read-only)

## Example prompts

- "Show me the trending prompts on LivePair right now"
- "Find anime portrait prompts and show the models they used"
- "Which model is cheapest for a 5 second image-to-video clip?"
- "Improve this prompt and quote the price to generate it as an image"

## Install

### Claude Code

1. Run this in a terminal, in your project folder:

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

2. Start Claude Code and type `/mcp`. **livepair** should show as connected.

Add `--scope user` to make it available in every project, not just this one.

### Claude Desktop

1. Open **Customize → Connectors**, click **+ Add**, then **Add custom connector**.

2. Name it **LivePair** and paste this URL:

```url
https://livepairai.com/mcp
```

3. Click **Add**. Its tools appear in the chat’s tools menu.

Claude Desktop’s JSON config file only starts local servers. Remote servers go through Connectors, and connectors you add on claude.ai show up here too.

### claude.ai

1. Open the connector form on claude.ai. This button fills in the name and URL for you:

[Add to claude.ai](<https://claude.ai/customize/connectors?modal=add-custom-connector&connectorName=LivePair&connectorUrl=https%3A%2F%2Flivepairai.com%2Fmcp>) (opens connector settings)

2. Check that the URL reads `https://livepairai.com/mcp` and click **Add**.

3. Turn it on in a chat from the tools menu.

Free plans allow one custom connector. On Team and Enterprise plans an owner adds it under **Organization settings → Connectors**.

### ChatGPT

1. On chatgpt.com, go to **Plugins**, select **+**, then **Add custom MCP server**.

2. Enter a name for the server.

3. Under **Connection**, paste `https://livepairai.com/mcp` as the server URL, then for authentication choose **No authentication**.

4. Check **I understand and want to continue**, then select **Create as a plugin**.

Whether you can add a custom MCP server depends on your ChatGPT plan and your workspace permissions (in Business workspaces, admins and owners can).

### Cursor

[Add to Cursor](<https://cursor.com/install-mcp?name=livepair&config=eyJ1cmwiOiJodHRwczovL2xpdmVwYWlyYWkuY29tL21jcCJ9>) (opens Cursor)

Or add it by hand to `~/.cursor/mcp.json` (all projects) or `.cursor/mcp.json` (this project):

`mcp.json`:

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

### VS Code

[Install in VS Code](<https://vscode.dev/redirect/mcp/install?name=livepair&config=%7B%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Flivepairai.com%2Fmcp%22%7D>) (opens VS Code)

Or from a terminal:

```bash
code --add-mcp '{"name":"livepair","type":"http","url":"https://livepairai.com/mcp"}'
```

Or commit it to the repo in `.vscode/mcp.json`:

`.vscode/mcp.json`:

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

### Devin Desktop

1. Add it to `~/.config/devin/mcp_config.json` (macOS and Linux) or `%APPDATA%\devin\mcp_config.json` (Windows):

`mcp_config.json`:

```json
{
  "mcpServers": {
    "livepair": {
      "serverUrl": "https://livepairai.com/mcp"
    }
  }
}
```

2. Refresh the MCP server list in Cascade.

Devin Desktop is the new name for Windsurf. It reads `serverUrl` (or `url`) for remote servers.

### Codex

```bash
codex mcp add livepair --url https://livepairai.com/mcp
```

Or edit `~/.codex/config.toml` directly:

`config.toml`:

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

### Gemini CLI

```bash
gemini mcp add --transport http livepair https://livepairai.com/mcp
```

This adds it to the current project. Add `-s user` to use it everywhere.

### Any client

Most clients accept this shape. Some name the URL field differently: `serverUrl` in Devin Desktop, `httpUrl` in Gemini CLI’s settings file.

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

Zed puts servers under `context_servers` in its settings. Cline needs `"type": "streamableHttp"`, or it assumes SSE.

Client only starts local servers? Bridge it with `npx -y mcp-remote https://livepairai.com/mcp`.

## Recent changes

- 2026-10-26 17:30 UTC: Tracking started: 14 tools read. Source: automatic check.

More on the History tab, with descriptions before and after for the newest entries: https://mcp.tc/i/livepair#history (Atom feed: https://mcp.tc/i/livepair/history.xml). It records what mcp.tc's anonymous checks saw, every 3 hours where the tool list can be read without sign-in; it is not a security review.

## Details

- Server version: 0.1.0
- MCP protocol version: 2025-11-25
- Last checked: 2026-11-17 (reachable)
- Listed: 2026-10-26
- Updated: 2026-10-26

---
Source: https://mcp.tc/i/livepair (mcp.tc is an independent directory, not affiliated with this server's publisher). Corrections: https://mcp.tc/report
