AI Visibility MCP

ai-visibility-mcp

MCP server that audits and fixes how AI sees your website. Robots, schema, LLM mentions, Cloudflare AI defaults — audit the problem, generate the fix, re-audit in one loop.

Most websites are accidentally invisible to AI search. Cloudflare's bot-management defaults block GPTBot / ClaudeBot / PerplexityBot. SPAs render an empty <div id="root"> to crawlers that don't run JS. Marketing teams have no idea their brand isn't surfacing in ChatGPT, Claude, or Perplexity answers — until traffic dries up.

ai-visibility-mcp closes the audit-and-fix loop inside a single agent session:

1. Audit — find what's blocking AI visibility
2. Fix — generate the artifact that corrects it
3. Paste — site owner applies the output
4. Re-audit — verify the fix was picked up

Tools

Audit tools

Generator tools (v0.3)

Why this exists

• Cloudflare flipped defaults in 2024-2025 to block AI scrapers. Most site owners never updated their config, so AI bots get challenged and bounce.
• MCP marketplaces shipped in 2026 (MCP Hive, Smithery, mcp.so, Glama). Every AI agent needs tools that can audit the real web. This is one.
• Brand visibility in LLM answers is the new SEO. Nobody has a clean stack for measuring it from a single MCP call.

Install

Requires Python 3.10+ and uv.

git clone https://github.com/bestaiinsider/ai-visibility-mcp
cd ai-visibility-mcp
uv sync
cp .env.example .env  # fill in PERPLEXITY_API_KEY / OPENROUTER_API_KEY

Run

# stdio transport — Claude Desktop / Claude Code
uv run ai-visibility-mcp

# HTTP transport — remote agents
uv run ai-visibility-mcp --http --port 8000

Claude Desktop / Claude Code config

Add to ~/Library/Application Support/Claude/claude_desktop_config.json (Desktop) or ~/.claude.json (CLI):

{
  "mcpServers": {
    "ai-visibility": {
      "command": "uv",
      "args": ["--directory", "/absolute/path/to/ai-visibility-mcp", "run", "ai-visibility-mcp"]
    }
  }
}

Audit-and-fix loop

# Step 1 — audit
> audit_ai_visibility(domain="example.com")
  score: 55
  warnings:
    - "9/22 AI bots disallowed — site largely invisible to AI search"
    - "no JSON-LD structured data — LLMs lose entity grounding"
    - "no /llms.txt found at root"

# Step 2 — generate fixes
> generate_robots_patch(domain="example.com")
  → new_robots: "User-agent: GPTBot\nAllow: /\n\nUser-agent: ClaudeBot\nAllow: /\n..."
  → diff:       unified diff of exactly what changed
  → paste_target: "/robots.txt at site root, replaces existing"

> generate_json_ld(url="https://example.com/")
  → page_type_detected: "Organization"
  → script_tag: '<script type="application/ld+json">{"@context":"https://schema.org","@type":"Organization"...}</script>'
  → paste_target: "inside <head> of the page"

> generate_llms_txt(domain="example.com")
  → content: "# Example Corp\n\n> One-sentence summary...\n\n## Pages\n- [Home](...): ..."
  → paste_target: "/llms.txt"

# Step 3 — site owner pastes the three artifacts

# Step 4 — re-audit
> audit_ai_visibility(domain="example.com")
  score: 95   ← was 55

Example session

> check_ai_bot_access(domain="bandcamp.com")

  summary: { total: 22, allowed: 13, disallowed: 9 }
  warnings: ["9/22 AI bots disallowed — site largely invisible to AI search"]
  blocked:  ["GPTBot", "ClaudeBot", "Google-Extended", "Bytespider",
             "CCBot", "Meta-ExternalAgent", "FacebookBot", "Amazonbot", "Diffbot"]

> audit_ai_visibility(domain="bandcamp.com")

  score: 49
  reasons:
    -36: 9 AI bots disallowed in robots.txt
    -10: no JSON-LD structured data
    -5:  no /sitemap.xml

> check_llm_mention(brand="Anthropic", query="Who makes the leading foundation AI models?")

  share_of_voice: 0.667
  by_model:
    perplexity/sonar          mentioned=true   citations=3
    openrouter/gpt-4o-mini    mentioned=true   citations=0
    openrouter/gemini-flash   mentioned=false  citations=0
  est_total_cost_usd: 0.00088
  daily_spend_usd:    0.00088 / $5.00 cap

Security posture

This server makes outbound HTTP requests to caller-supplied domains and to LLM providers. v0.2 hardening:

• SSRF guard. All outbound HTTP refuses loopback, link-local (AWS / GCP / Azure metadata IPs), RFC1918, CGNAT, and IPv6 ULA addresses. Redirects are re-validated.
• Daily spend cap. LLM calls are gated by MAX_DAILY_USD (default $5.00), persisted to ~/.cache/ai-visibility-mcp/spend.json. Loop-amplification can't drain your Perplexity / OpenRouter credits.
• Per-call cost ceiling. MAX_COST_PER_CALL (default $0.10) plus LLM_MAX_OUTPUT_TOKENS (default 1024) hard-bounds any single tool invocation.
• No persistence of user content. Nothing is logged to disk except the daily spend totals.

Configuration

Development

uv sync --extra dev
uv run pytest          # 40 tests
uv run ruff check .    # lint

Status

v0.3 — audit + fix loop complete. 7 tools (4 audit + 3 generator), 40/40 tests, SSRF-hardened, spend-capped. Smoke-verified against tealhq.com / bandcamp.com / anthropic.com.

License

MIT.