About Citehound
Citehound is an AI-readiness scanning service for website operators. Its free scan is read-only and can generate llms.txt, robots.txt, and schema, with reports and implementation services described as additional offerings.
Key features
- 01Scan a site's AI readiness
- 02Generate llms.txt
- 03Generate robots.txt
- 04Generate schema
- 05Run a free read-only scan
Use cases
- 01Check a website's AI readiness
- 02Generate llms.txt and robots.txt for a site
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://getcitehound.com/api/mcpclaude mcp add --transport http andacuzel-citehound https://getcitehound.com/api/mcp{"mcpServers":{"andacuzel-citehound":{"type":"http","url":"https://getcitehound.com/api/mcp"}}}Open in Cursor{"servers":{"andacuzel-citehound":{"type":"http","url":"https://getcitehound.com/api/mcp"}}}Open in VS Code{"mcpServers":{"andacuzel-citehound":{"type":"http","url":"https://getcitehound.com/api/mcp"}}}{"mcpServers":{"andacuzel-citehound":{"serverUrl":"https://getcitehound.com/api/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
Details
From the project READMEcited-geo-guide
This repository holds Citehound, an end-to-end service for AI readiness: a free scanner, Pro site reports, Fix (we make the technical changes) and Beyond (we write the content). The repository and the Vercel project keep their original names; see docs/rename-notes.md.
Benchmark data
The homepage benchmark section (and the "average of N sites" line on every scan report) is generated, not hand-written. To add a category:
- Scan it:
node scripts/scan-category.js domains/<category>.txt <category>— writesdata/<category>-raw.json(per-domain results — gitignored, never published) anddata/<category>-summary.json(aggregate stats only, no company names). - Add one entry to
data/benchmarks.json:category(matches the summary filename),label(display name),track("B2B SaaS"or"Consumer & e-commerce"),note(the unit word for the sample size, e.g."platforms"). - Run
node scripts/generate-benchmarks.js— rewrites the block inindex.htmlbetween theBENCHMARKS:START/BENCHMARKS:ENDmarkers. Safe to re-run; it replaces the block in place. - Commit
data/benchmarks.json, the newdata/<category>-summary.json, and the regeneratedindex.html. Leave-raw.jsonuncommitted — it's gitignored on purpose.
No score or count is ever typed by hand into benchmarks.json or
index.html — both are read from the summary file at generation time,
so they can't drift apart. Two minutes, no HTML editing.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.