What is ai-visibility-mcp CLAUDE.md?

A project instruction file for building an AI-visibility MCP server. MCP is a standard way for an AI assistant to call external tools; here, the tools check whether websites and brands appear in AI search results.

Use it when developing the server, including checks for AI-bot access, brand mentions, website visibility, and competitor comparisons.

It gives the coding agent the project's intended tools, technology choices, external services, and build order in one place.

How bestaiinsider/ai-visibility-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to bestaiinsider/ai-visibility-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/bestaiinsider/ai-visibility-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/bestaiinsider/ai-visibility-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/bestaiinsider/ai-visibility-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/bestaiinsider/ai-visibility-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/bestaiinsider/ai-visibility-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/bestaiinsider/ai-visibility-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/bestaiinsider/ai-visibility-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/bestaiinsider/ai-visibility-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 870 This file is loaded in full into every session.

When invoked 870 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00870	$0.00870
Opus 5.5	$0.00348	$0.00348
Sonnet 5.5	$0.00174	$0.00174
Haiku 4.5	$0.00087	$0.00087

Measured 2mo ago against content hash 8797f0918e6d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ai-visibility-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI-Visibility MCP — Project Instructions

Project-scoped CLAUDE.md. User-scope durable rules at ~/.claude/CLAUDE.md still apply. Project tracker / lifecycle / decisions live in vault: ~/Documents/Vault/02 Projects/ai-visibility-mcp.md

What this builds

A paid Model Context Protocol server that exposes AI-search-visibility data: which AI bots can read a site, whether brands surface in LLM-generated answers, and whether Cloudflare's AI-bot defaults are accidentally blocking the site from AI search.

Tools the MCP exposes (target API)

check_ai_bot_access(domain) — robots.txt + headers per-bot
check_llm_mention(brand, query) — does the brand surface in Perplexity / Tavily / OpenRouter LLM answers
audit_ai_visibility(domain) — composite report
compare_competitors(your_domain, competitor_domains) — side-by-side
track_changes(domain) — diff over time (v2, needs persistence)

Stack

Language: Python 3.10+ (FastMCP)
Package mgmt: uv
Dependencies: fastmcp, httpx, python-dotenv, pyyaml
External APIs (credentials in ~/Setup/credentials.md):
- Perplexity (LLM-aware search)
- Tavily (LLM-grounded web search)
- OpenRouter (cross-model LLM checks: Claude, GPT, Gemini)
- Firecrawl (page scrape for tag/structured-data audit)
Transport: stdio + HTTP (FastMCP supports both)

Build phase order

Skeleton + check_ai_bot_access (offline-ish, just HTTP requests)
audit_ai_visibility composite
check_llm_mention (uses Perplexity + OpenRouter)
compare_competitors
README + listing on Smithery / mcp.so / Glama (free)
Paid backend via MCPize (gated tools behind license key)
Direct customer-facing audit subscription (separate web app, reuses MCP backend)

Test before claim

Three real domains for E2E tests:

tealhq.com (known-AI-friendly)
bandcamp.com (known to block aggressively)
Whatever Kris's primary domain ends up being

Each tool must produce output against all three before being marked done.

Read the full file on GitHub · 83 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 83 lines · 870 tokens per session scan A 8797f0918e6d

Subscribe to this mod's changes

ai-visibility-mcp CLAUDE.md is an instructions file published in the GitHub repository bestaiinsider/ai-visibility-mcp (1 stars, last pushed 5mo ago), licensed MIT. It adds 870 tokens to every session, about $0.0035 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Marketing and SEO

ai-visibility-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ai-visibility-mcp CLAUDE.mdbestaiinsider/ai-visibility-mcp	Instructions file	1	5mo ago	MIT	A	870	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,685	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

ai-visibility-mcp: Instructions file for Claude Code