# Howseen

Howseen brings brand visibility data from AI answers into an assistant. Use it to inspect mentions, rival brands and cited sources, then work with related content.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI
- Author: howseen-ai
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/howseen-ai/howseen-mcp
- Updated: 2026-10-20
- HTML: https://affpapa.org/en/nevibecode/mcp/howseen

## What it does

The remote MCP server gives an assistant access to Howseen account data. It can show how often AI engines mention a brand, compare its presence with competitors, and surface buyer questions where a rival appears instead. You can also inspect cited domains and changes between scans.

Some tools can alter account data. They cover tasks such as adding tracked questions, drafting an article and publishing it to a connected site. Each action displays a preview first; it only goes through with `confirm: true`. These tools require a Howseen API key that allows actions.

The server connects over HTTP. An API key is needed to access account data, so setup alone does not grant access. Article publishing can target a connected WordPress, Shopify, Ghost, BigCommerce site, a webhook, or a Howseen-hosted blog.

## Requirements
- Remote server: `https://app.howseen.ai/api/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http howseen https://app.howseen.ai/api/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add howseen --url https://app.howseen.ai/api/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "howseen": {
            "url": "https://app.howseen.ai/api/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "howseen": {
            "type": "http",
            "url": "https://app.howseen.ai/api/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http howseen https://app.howseen.ai/api/mcp
```

## When to use it
- Check how often AI answers mention a brand
- Find buyer questions where a competitor appears instead
- See which domains AI engines cite
- Draft an article and publish it to a connected site
- Review changes between scans

## Example prompts
- Show our brand's visibility across AI engines.
- Find buyer questions where ChatGPT mentions a competitor but leaves us out.
- Draft an article about the question where we lose most often, then publish it to our connected site.

## Similar
- [ai-prompt-research](https://affpapa.org/en/nevibecode/skills/ai-prompt-research.md) — skill · 957 installs
- [Cite42](https://affpapa.org/en/nevibecode/mcp/cite42.md) — MCP server
- [optimize-for-ai](https://affpapa.org/en/nevibecode/skills/optimize-for-ai.md) — skill · 6600 installs
- [geo-content-optimizer](https://affpapa.org/en/nevibecode/skills/aaron-he-zhu-geo-content-optimizer.md) — skill · 1700 installs
- [programmatic-seo](https://affpapa.org/en/nevibecode/skills/coreyhaines31-programmatic-seo.md) — skill · 150800 installs

---
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