Ai Visibility Mcp

What is Ai Visibility Mcp?

Ai Visibility Mcp is an MCP server that audits how AI sees a website—checking robots.txt, structured data, LLM brand mentions, and Cloudflare AI defaults in a single tool call. It is built for website owners and marketing teams who need to understand and improve their site's visibility to AI search engines and chatbots.

How to use Ai Visibility Mcp?

Requires Python 3.10+ and uv. Clone the repository, run uv sync, copy .env.example to .env and fill in PERPLEXITY_API_KEY and OPENROUTER_API_KEY. Run with uv run ai-visibility-mcp for stdio transport (Claude Desktop/Code) or uv run ai-visibility-mcp --http --port 8000 for HTTP transport. Configure as an MCP server in Claude Desktop config or .claude.json.

Key features of Ai Visibility Mcp

• check_ai_bot_access(domain)—per-bot robots.txt analysis for 22 AI user-agents
• audit_ai_visibility(domain)—0–100 composite score with explainable deductions
• check_llm_mention(brand, query, aliases?, models?)—cross-model brand surfacing
• compare_competitors(your_domain, competitor_domains[])—parallel ranked audit, max 10 in flight
• SSRF guard, daily spend cap, and per-call cost ceiling

Use cases of Ai Visibility Mcp

• Determine whether AI bots (GPTBot, ClaudeBot, PerplexityBot) are blocked from your site
• Get an overall AI visibility score with line-item deductions for missing structure data or sitemaps
• Measure your brand's share of voice in LLM-generated answers across multiple models
• Benchmark your site's AI accessibility against up to 10 competitors simultaneously

FAQ from Ai Visibility Mcp

What dependencies and runtime requirements does Ai Visibility Mcp have?

Python 3.10+ is required, along with the uv package manager. For LLM brand-mention checks, PERPLEXITY_API_KEY and OPENROUTER_API_KEY must be set in the environment.

What data does Ai Visibility Mcp persist?

No user content is logged to disk. The only persistence is a daily spend ledger (default ~/.cache/ai-visibility-mcp/spend.json) used to enforce the MAX_DAILY_USD cap.

What transport and authentication options are available?

Ai Visibility Mcp supports stdio transport (for Claude Desktop/Code) and HTTP transport (for remote agents). No built-in authentication on the HTTP transport is mentioned; security relies on the SSRF guard and spend caps.

What are the known limits of Ai Visibility Mcp?

The compare_competitors tool supports a maximum of 10 domains in flight. LLM calls are bounded by a per-call cost ceiling (MAX_COST_PER_CALL, default $0.10) and a daily spend cap (MAX_DAILY_USD, default $5.00). Output tokens are capped at 1024 per call. Persistent diff tracking is deferred to a future release.