# Citehound (remote · getcitehound.com)

Scan any domain for AI readiness and generate llms.txt, robots.txt and schema. Free, read-only.

- Trust score: 81/100 (high trust)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `getcitehound.com`: 81/100 (this document), [markdown](https://verifymcp.io/servers/andacuzel-citehound/api-mcp.md), [page](https://verifymcp.io/servers/andacuzel-citehound/api-mcp)

## Channel facts

- Endpoint: `https://getcitehound.com/api/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Endpoint Security**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 82/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 2283 tokens (~175/item across 13 items; 13 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 47/100
  - Stability observed for 14 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 13 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 14 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the Citehound MCP server?

Citehound is a hosted endpoint at https://getcitehound.com/api/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http andacuzel-citehound 'https://getcitehound.com/api/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "andacuzel-citehound": {
      "url": "https://getcitehound.com/api/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "andacuzel-citehound": {
      "type": "http",
      "url": "https://getcitehound.com/api/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.andacuzel-citehound]
url = "https://getcitehound.com/api/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "andacuzel-citehound": {
      "type": "remote",
      "url": "https://getcitehound.com/api/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add andacuzel-citehound --url 'https://getcitehound.com/api/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  andacuzel-citehound:
    url: "https://getcitehound.com/api/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "andacuzel-citehound": {
      "Transport": "http",
      "Url": "https://getcitehound.com/api/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add andacuzel-citehound -t streamable-http -u 'https://getcitehound.com/api/mcp'
```

### Other

```json
{
  "mcpServers": {
    "andacuzel-citehound": {
      "type": "http",
      "url": "https://getcitehound.com/api/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-04 (score 81, +1)

No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-02 (score 80, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-30 (score 79, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-28 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-26 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-24 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-23 (score 75, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-10-22 (score 75)

First indexed and scored.

## MCP tools (13)

### `scan_site` (~261 tokens)

Scan a site for AI readiness

Scans a domain’s public robots.txt, llms.txt, sitemap declaration and homepage, and scores it out of 100 across three pillars: discoverability (can AI crawlers reach it), technical foundation (can machines parse it), and content & trust (does it look like a credible source). Returns the score, the three pillar scores, access state for the 10 tracked AI crawlers, every failed check with its fix, and how the score compares to Citehound’s own benchmark data. If the site looks like a store (two or more of five signals), it also reports a separate agentic-commerce sub-score: whether a UCP merchant profile exists at /.well-known/ucp, whether one product page has Product schema with name, price, availability and image, and whether the llms.txt looks like a platform default. That sub-score is never part of the 100. Call this first for any domain. It fetches the live site (a store scan reads up to one extra product page), so avoid calling it in a tight loop for the same domain.

Input parameters:

- `domain` (string, required): A bare domain, e.g. "example.com". No scheme (https://) and no path — the scan always targets the domain root.

### `compare_sites` (~88 tokens)

Compare two sites

Scans two domains — one after the other, not in parallel — and reports both scores plus every check where they differ. Useful for comparing your site against a named competitor.

Input parameters:

- `domain_a` (string, required): The first bare domain, e.g. "example.com".
- `domain_b` (string, required): The second bare domain, e.g. "competitor.com". Must differ from domain_a.

### `generate_schema` (~130 tokens)

Generate JSON-LD for a site

Fetches a domain’s homepage for its real title, meta description and declared language, then returns ready-to-paste JSON-LD structured data of the requested type. Fields the scan cannot know — a FAQ’s actual questions, a product’s real price — come back as clearly bracketed placeholders, never invented values.

Input parameters:

- `domain` (string, required): A bare domain, e.g. "example.com".
- `type` (string, required): "organization" returns Organization + WebSite schema as an @graph; the others (faqpage, article, product, localbusiness) each return one schema of that @type.

### `generate_robots_txt` (~156 tokens)

Generate an AI-crawler robots.txt

Builds a robots.txt file that explicitly allows or blocks named AI crawlers from Citehound’s tracked list of 10, plus an optional Sitemap line. Pure text generation — fetches nothing. Call list_ai_crawlers first if you need the exact tracked crawler names.

Input parameters:

- `allow` (array): Crawler names to explicitly allow, e.g. ["GPTBot", "ClaudeBot"]. Must be names from the tracked list.
- `block` (array): Crawler names to explicitly block. Must be names from the tracked list, and must not overlap with "allow".
- `sitemap_url` (string): Optional absolute sitemap URL to add as a Sitemap: line, e.g. "https://example.com/sitemap.xml".

### `generate_llms_txt` (~114 tokens)

Generate an llms.txt file

Builds an llms.txt file — an optional convention for describing a site and its key pages, with no demonstrated effect on Google — from a name, a one-sentence description and a list of key pages. Pure text generation — fetches nothing.

Input parameters:

- `description` (string, required): A one-sentence summary of what the site is.
- `key_pages` (array): Pages worth pointing an AI system to, most important first.
- `name` (string, required): The site or product name for the llms.txt header.

### `get_playbook` (~210 tokens)

Get a vertical playbook

Returns the full GEO/AEO playbook for one of Citehound’s fourteen verticals, as plain readable text: the strategic shift, three actionable strategies, outdated pitfalls to avoid, and an expert-tip placeholder. Called with no argument it returns the list of the fourteen verticals with their track (B2B SaaS, consumer and e-commerce brands, local and independent professionals), so call it with no argument first when you do not know which vertical fits. Read from this project’s own content file, so it matches what a visitor to the site sees. Fetches nothing external. Use after scan_site to turn a failed check into the strategy that applies to the site’s category.

Input parameters:

- `vertical` (string): Optional. A vertical slug. B2B SaaS: crm, martech, hrtech, fintech, cybersecurity, devtools. Consumer brands: ecommerce, consumerapps, hospitality, marketplaces. Professionals: health, localservices,…

### `get_benchmark` (~122 tokens)

Get category benchmark data

Returns Citehound’s own archived scan data for one category — average, median and range of scores, pillar breakdowns, per-crawler blocked, limited and open counts, and the most common failed checks, with sample size and scan date — or a ranked summary across every category when called with no argument. This is archived data, not a live scan, and fetches nothing external.

Input parameters:

- `category` (string): Optional. One of: crm, cybersecurity, devtools, dtc-brands, consumer-apps, hospitality. Omit to get every category.

### `list_ai_crawlers` (~64 tokens)

List tracked AI crawlers

Lists the 10 AI crawlers Citehound tracks: which company runs each, what allowing or blocking it means, and this project’s robots.txt generator’s default for it. Use before generate_robots_txt if you need the exact tracked names. Fetches nothing.

### `get_citation_prompts` (~329 tokens)

Get citation questions for a vertical

Returns the set of buying-intent questions Citehound uses to test whether an AI assistant names a brand, for one vertical, plus a short protocol a person can run in their own assistant: ask each question in a separate conversation three to five times, note whether the brand is named and whether it appears in a heading, list label, table or bold text, and judge the spread rather than one answer. The questions don’t name any brand in the category being measured. A few mention an integration platform such as Slack or Google Workspace, because that is how buyers ask. Read-only: it reads a content file and queries no model. There is deliberately no tool that runs the check for you: a run is about 90 model calls at about five seconds each, far past this server’s time limit, and it would spend a quota anyone could drain. Question sets exist for: consumerapps, crm, cybersecurity, devtools, ecommerce, fintech, health, hospitality, hrtech, legal, localservices, marketplaces, martech, realestate. Use when the user asks how to check whether an assistant names their brand, or wants the questions for their category.

Input parameters:

- `vertical` (string, required): A vertical slug. Valid: consumerapps, crm, cybersecurity, devtools, ecommerce, fintech, health, hospitality, hrtech, legal, localservices, marketplaces, martech, realestate. Question sets exist for:…

### `get_citation_sample` (~155 tokens)

Get the anonymised citation sample

Returns Citehound’s anonymised sample citation run as readable text: the model, the date, how many times each question was asked, the questions in three groups (named in every try, unstable, never named), the overall rate of being named with its range across sweeps, and a note on the limits. It is one model on one date, so it is not a ranking, says nothing about other assistants and is not a forecast of traffic. It names no brand in the category being measured, no domain and no competitor. Read-only: it reads a content file and queries no model. Use when the user wants to see what a citation result looks like, or asks how much the same question varies between tries.

### `get_methodology` (~217 tokens)

Get the scoring methodology

Explains how the Citehound AI readiness score is built, read from the scanner’s own check registry so it matches what runs. With no argument it returns the three pillars with their weights (they add up to 100), every check with its category, points, what it tests and why it matters, and the limits of the scan: it measures readiness and not whether any assistant names a brand; it gives half credit for a crawler with any applicable Disallow rule, usually an ordinary path; and it reads the homepage only. With a check label it returns that one check in detail. An unknown label returns an error listing the valid labels. Read-only, fetches nothing external. Use when the user asks how a score is calculated, why a check carries the points it does, or what the scan cannot tell them.

Input parameters:

- `check` (string): Optional. A check label exactly as scan_site reports it, e.g. "Page title" or "AI crawler access". Case does not matter. Omit for the whole methodology.

### `get_research` (~167 tokens)

Get Citehound research

Returns Citehound’s published research: with no argument, the list of reports (the llms.txt and crawler study, the AgaOne case study and the benchmark data) with title, date, one-line finding and URL; with a slug, the key findings, the method limits, the URL and a ready line for citing it. Findings are checked against the published pages and data files. Every study measures readiness inputs, not whether any assistant names a brand. Read-only, fetches nothing external. Use when the user wants evidence for a claim about AI crawler access or llms.txt, a statistic to cite, or the reports behind the benchmarks.

Input parameters:

- `slug` (string): Optional. A report slug from the list this tool returns with no argument. Omit to list the reports.

### `get_sample_report` (~171 tokens)

Get the sample full-site report

Returns the sample Pro report as readable text: a real crawl of Citehound’s own site on a stated date, with the results shown as recorded. It gives the whole-site score beside the homepage score, the pillar averages, the priorities from the executive summary with the label saying what wrote it, the checks failing by number of pages, and the link to the full report, which also lists every page alphabetically and gives an estimated score if the fixes are applied. It shows what a full-site crawl adds to a one-page scan. It is our own site, not a customer’s, and it measures readiness, not whether any assistant names the site. Read-only, fetches nothing external. Use when the user asks what a full-site report looks like or what a crawl shows that a homepage scan cannot.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/andacuzel-citehound/api-mcp#diagnostics

## Score history

- 2026-11-05: 81
- 2026-11-04: 81
- 2026-11-03: 80
- 2026-11-02: 80
- 2026-11-01: 79
- 2026-10-31: 79
- 2026-10-30: 79
- 2026-10-29: 78
- 2026-10-28: 78
- 2026-10-27: 77
- 2026-10-26: 77
- 2026-10-25: 76
- 2026-10-24: 76
- 2026-10-23: 75
- 2026-10-22: 75

## Common questions

### What is the Citehound MCP server?

Citehound is an MCP server listed in the public MCP registry as io.github.andacuzel/citehound. Scan any domain for AI readiness and generate llms.txt, robots.txt and schema. Free, read-only. This page covers its hosted endpoint (https://getcitehound.com/api/mcp).

### Is the Citehound MCP server safe to use?

Citehound scores 81 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Citehound MCP server expose?

Citehound exposes 13 tools: scan_site, compare_sites, generate_schema, generate_robots_txt, generate_llms_txt, and 8 more. Their descriptions and schemas cost roughly 2,184 tokens of context every time the server is loaded.

### Does the Citehound MCP server require authentication?

No. We connected to Citehound without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Citehound MCP server still maintained?

Citehound is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://getcitehound.com/api/mcp
- Repository: https://github.com/andacuzel/cited-geo-guide
- Website: https://getcitehound.com/claude
- Changelog RSS feed: https://verifymcp.io/servers/andacuzel-citehound/api-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/andacuzel-citehound/api-mcp.json
- HTML version of this page: https://verifymcp.io/servers/andacuzel-citehound/api-mcp