Citehound

Citehound checks whether AI assistants can reach, read and understand a website, then writes the files that close the gaps.

Ask your AI to scan a domain and it reads the site's public robots.txt, llms.txt, sitemap declaration and homepage. You get a score out of 100, the access state of 10 tracked AI crawlers (GPTBot, ClaudeBot, PerplexityBot and others), and every failed check with the fix next to it.

What you can ask

Returns the buying-intent question set for a vertical and the protocol for running it yourself in any assistant, five tries per question, and what to record.
Example path

MCP connector

Server URL: https://getcitehound.com/api/mcp
Login: None
Protocol: MCP 2026-07-28
Instructions: Citehound scans a domain’s public robots.txt, llms.txt and homepage for AI-crawler access and on-page signals, and generates the fixes (schema, robots.txt, llms.txt). It also serves the scoring methodology, the research, a sample report of our own site, the vertical playbooks and the citation question sets, and three prompts for common workflows. Every tool is read-only and non-destructive. It measures readiness, not whether any assistant names a brand.

Tools

Reads data13

Skills

None in the store listings or on the server

What you can ask

Returns the buying-intent question set for a vertical and the protocol for running it yourself in any assistant, five tries per question, and what to record.

Example path

MCP connector

Server URL

https://getcitehound.com/api/mcp

None

Protocol

MCP 2026-07-28

Instructions

Citehound scans a domain’s public robots.txt, llms.txt and homepage for AI-crawler access and on-page signals, and generates the fixes (schema, robots.txt, llms.txt). It also serves the scoring methodology, the research, a sample report of our own site, the vertical playbooks and the citation question sets, and three prompts for common workflows. Every tool is read-only and non-destructive. It measures readiness, not whether any assistant names a brand.