# ai-visibility

Tracks how Claude, Perplexity, Claude and Gemini mention a brand: how often, where, and in what tone. Useful when you need a read on AI answer visibility.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 11
- Author: sharozdawa
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/sharozdawa/ai-visibility
- Updated: 2026-03-22
- HTML: https://affpapa.org/en/nevibecode/mcp/ai-visibility

## What it does

The server hands your agent six tools for checking a brand across four AI platforms. You can pull a 0–100 visibility score with a per-platform breakdown, test a single query for a mention, pit up to 10 brands against each other, or ask for prioritized fixes. A separate call lists the platforms and explains where each one draws its information from.

Setup is a single `npx` line: the package launches over stdio and plugs into any MCP client. Prefer your own build? Clone the repo, run `npm install` and `npm run build` inside `mcp-server`, then point the client at `dist/index.js`. There is also a Next.js dashboard, and that part needs a `DATABASE_URL` in `.env`.

The score is weighted: mention frequency counts 40%, position quality 30%, sentiment 30%. Same brand in, same number out — the server uses seeded pseudo-randomness. Handy for tracking a trend over weeks, though it also tells you the figures come from the server's model rather than a live poll of the platforms.

## Requirements
- Needs: Node.js (commands run via npx)

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add ai-visibility -- npx -y ai-visibility-mcp
```

### Codex

**Platform CLI**
```bash
codex mcp add ai-visibility -- npx -y ai-visibility-mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "ai-visibility": {
            "command": "npx",
            "args": [
                "-y",
                "ai-visibility-mcp"
            ]
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "ai-visibility": {
            "type": "stdio",
            "command": "npx",
            "args": [
                "-y",
                "ai-visibility-mcp"
            ]
        }
    }
}
```

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add ai-visibility npx -y ai-visibility-mcp
```

## When to use it
- find out whether AI platforms mention your brand at all
- benchmark visibility against named competitors
- see the tone models use when they discuss your brand
- get a visibility score plus a ranked fix list
- test one specific query on one specific platform

## Example prompts
- Check brand visibility for “Acme” across the AI platforms
- Use `compare_brands` to rank Acme against two competitors
- Pull recommendations based on the current visibility score

## Similar
- [New-Term Radar](https://affpapa.org/en/nevibecode/mcp/new-term-radar.md) — MCP server · ★ 1823
- [NotFair](https://affpapa.org/en/nevibecode/mcp/notfair.md) — MCP server · ★ 4064
- [seo-monster](https://affpapa.org/en/nevibecode/mcp/seo-monster.md) — MCP server · ★ 555
- [Google Maps MCP Server](https://affpapa.org/en/nevibecode/mcp/google-maps-mcp-server.md) — MCP server · ★ 484
- [Search Console MCP](https://affpapa.org/en/nevibecode/mcp/search-console-mcp.md) — MCP server · ★ 310
- [squirrelscan](https://affpapa.org/en/nevibecode/mcp/squirrelscan.md) — MCP server · ★ 298

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md