Gives Claude six MCP tools to track how your brand shows up in ChatGPT, Perplexity, Claude, and Gemini responses. You can run check_brand_visibility to get mention rates, positioning, and sentiment across all platforms, or use check_single_query to test specific prompts on individual AIs. The compare_brands tool benchmarks you against up to 10 competitors, while get_visibility_score returns a 0-100 rating based on mention frequency, position quality, and sentiment. Recommendations are prioritized and actionable. Uses seeded randomness for reproducible results. This is the MCP interface to an open source alternative to paid AI visibility tools like Otterly and AthenaHQ.
Know exactly how AI platforms talk about your brand.
Track mentions, sentiment, position, and competitors across the AI platforms that shape buying decisions.
Add to your claude_desktop_config.json:
{
"mcpServers": {
"ai-visibility": {
"command": "npx",
"args": ["-y", "ai-visibility-mcp"]
}
}
}
Add to your Cursor MCP settings (.cursor/mcp.json):
{
"mcpServers": {
"ai-visibility": {
"command": "npx",
"args": ["-y", "ai-visibility-mcp"]
}
}
}
npx ai-visibility-mcp
| 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 |
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:
Clone the repo and build the MCP server:
git clone https://github.com/sharozdawa/ai-visibility.git
cd ai-visibility/mcp-server
npm install
npm run build
Run the MCP server directly:
node dist/index.js
Or point your MCP client to the local build:
{
"mcpServers": {
"ai-visibility": {
"command": "node",
"args": ["/path/to/ai-visibility/mcp-server/dist/index.js"]
}
}
}
The project includes a Next.js dashboard for visual tracking:
cd ai-visibility
cp .env.example .env
# Set your DATABASE_URL in .env
npm install
npx prisma db push
npm run dev
| Platform | Company | How It Sources Information |
|---|---|---|
| ChatGPT | OpenAI | Trained on web data; optional web browsing for real-time info |
| Perplexity | Perplexity AI | Real-time web search with source citations |
| Claude | Anthropic | Trained on web data; focuses on accurate, well-reasoned responses |
| Gemini | Leverages Google Search index and Knowledge Graph |
| Feature | ai-visibility | Otterly | AthenaHQ |
|---|---|---|---|
| Platforms tracked | 4 | 3 | 2 |
| Visibility score | Yes | Yes | Yes |
| Competitor analysis | Yes | Yes | Limited |
| Sentiment analysis | Yes | No | No |
| Self-hostable | Yes | No | No |
| Open source | Yes | No | No |
| Price | Free | $100-300/mo | $200-500/mo |
| Tool | Description |
|---|---|
| awesome-seo-mcp-servers | Curated list of SEO MCP servers and agent skills |
| robotstxt-ai | Visual robots.txt manager for AI crawlers |
| indexnow-mcp | Instant URL indexing via IndexNow |
| schema-gen | Schema.org JSON-LD markup generator |
MIT
Built by Sharoz Dawa
io.github.ericm1018/skillfm-llm-cost-optimizer-openai-anthropic-usage
io.github.mikerawsonnz/llm-orchestration-agent
io.github.mikerawsonnz/authenticated-llm-agent
labforgedev/copilot-memory-mcp
csoai-org/agent-prompt-injection-firewall-mcp
io.github.mikerawsonnz/authenticated-multi-llm-agent