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.
@krissanders
Basic information
MCP server that audits AI-bot visibility. Reports per-bot robots.txt verdicts for 22 AI user-agents (GPTBot, ClaudeBot, PerplexityBot, Google-Extended, etc.), Cloudflare AI-default flags, on-page schema, sitemap, llms.txt, SPA-shell detection, and cross-model brand mentions via P
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"ai-visibility": {
"command": "uv",
"args": [
"--directory",
"/abs/path/to/ai-visibility-mcp",
"run",
"ai-visibility-mcp"
],
"env": {
"PERPLEXITY_API_KEY": "<your-key>",
"OPENROUTER_API_KEY": "<your-key>"
}
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
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.
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.
check_ai_bot_access(domain)—per-bot robots.txt analysis for 22 AI user-agentsaudit_ai_visibility(domain)—0–100 composite score with explainable deductionscheck_llm_mention(brand, query, aliases?, models?)—cross-model brand surfacingcompare_competitors(your_domain, competitor_domains[])—parallel ranked audit, max 10 in flightPython 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.
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.
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.
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.
🚀 The fast, Pythonic way to build MCP servers and clients.
Senso MCP turns a Joomla 5 or 6 site into a remote MCP server. It runs inside Joomla itself (no extra server, no Node.js bridge) and is secured with OAuth 2.1 and Joomla's own ACL. The free pack lets an AI assistant crea
YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context

Couples therapist Figs O'Sullivan (LMFT, 17 years, endorsed by Sue Johnson, creator of EFT) inside your AI. Ask relationship questions answered from his clinical writing, name the pattern in a fight, get a three-step rep
Painless E2E Automation for Mobile and Web
Comments