sharozdawa/ai-visibility

Track mentions, sentiment, position, and competitors across the AI platforms that shape buying decisions.
---
Features
- **Multi-Platform Tracking** — Monitor visibility across ChatGPT, Perplexity, Claude, and Gemini simultaneously
- **Visibility Scoring** — Get a 0-100 score with tier ratings (Excellent / Good / Moderate / Low / Very Low)
- **Sentiment Analysis** — Understand whether AI platforms describe your brand positively, neutrally, or negatively
- **Competitor Intelligence** — See which competitors appear alongside your brand in AI responses
- **Brand Comparison** — Compare up to 10 brands side by side with per-platform breakdowns
- **Actionable Recommendations** — Get prioritized steps to improve your AI visibility
- **MCP Server** — Works with Claude Desktop, Cursor, and any MCP-compatible client
- **Consistent Results** — Seeded randomness ensures reproducible results for the same brand
MCP Server Installation
Claude Desktop
Add to your claude_desktop_config.json:
Cursor
Add to your Cursor MCP settings (.cursor/mcp.json):
npx (standalone)
MCP Tools
| Tool | Description |
|------|-------------|
| check_brand_visibility | Check a brand's visibility across AI platforms with detailed per-platform results, mention rates, positions, sentiment, and competitor analysis |
| check_single_query | Check brand mention for a specific query on a specific platform — get mention status, position, context snippet, and sentiment |
| get_visibility_score | Calculate overall AI visibility score (0-100) with tier rating, per-platform breakdowns, and improvement recommendations |
| compare_brands | Compare visibility of 2-10 brands side by side with ranked results and per-platform scores |
| get_recommendations | Get prioritized, actionable recommendations to improve AI visibility based on current score |
| list_platforms | List all supported AI platforms with details on how each sources and presents brand information |
How Scoring Works
The visibility score (0-100) is calculated from three components:
| Component | Weight | What It Measures |
|-----------|--------|-----------------|
| Mention Rate | 40% | How often the brand appears in AI responses |
| Position Quality | 30% | Where the brand is mentioned (1st = best, 5th = worst) |
| Sentiment | 30% | Whether mentions are positive, neutral, or negative |
**Score Tiers:**
- **80-100** Excellent — Strong presence across platforms
- **60-79** Good — Visible but room to improve
- **40-59** Moderate — Appears in some responses
- **20-39** Low — Limited visibility
- **0-19** Very Low — Rarely mentioned
Self-Hosting
Clone the repo and build the MCP server:
Run the MCP server directly:
Or point your MCP client to the local build:
Run the Web Dashboard
The project includes a Next.js dashboard for visual tracking:
Platforms Tracked
| Platform | Company | How It Sources Information |