# CrawlCheck (remote · crawlcheck.io)

Verification layer for the agentic web: a signed answer about any site before an agent acts.

- Trust score: 82/100 (high trust)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `crawlcheck.io`: 82/100 (this document), [markdown](https://verifymcp.io/servers/emmanuelorta-crawlcheck/crawlcheck.md), [page](https://verifymcp.io/servers/emmanuelorta-crawlcheck/crawlcheck)

## Channel facts

- Endpoint: `https://crawlcheck.io/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.1.0`

## 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**: 77/100
  - 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.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC is configured correctly; the domain's records validate against the full chain to the root.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 67/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 2966 tokens (~118/item across 25 items; 25 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 83/100
  - Stability observed for 25 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 90/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 69% 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 25 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 26 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

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

CrawlCheck is a hosted endpoint at https://crawlcheck.io/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 emmanuelorta-crawlcheck 'https://crawlcheck.io/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "emmanuelorta-crawlcheck": {
      "url": "https://crawlcheck.io/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "emmanuelorta-crawlcheck": {
      "type": "http",
      "url": "https://crawlcheck.io/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.emmanuelorta-crawlcheck]
url = "https://crawlcheck.io/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "emmanuelorta-crawlcheck": {
      "type": "remote",
      "url": "https://crawlcheck.io/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add emmanuelorta-crawlcheck --url 'https://crawlcheck.io/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  emmanuelorta-crawlcheck:
    url: "https://crawlcheck.io/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "emmanuelorta-crawlcheck": {
      "Transport": "http",
      "Url": "https://crawlcheck.io/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add emmanuelorta-crawlcheck -t streamable-http -u 'https://crawlcheck.io/mcp'
```

### Other

```json
{
  "mcpServers": {
    "emmanuelorta-crawlcheck": {
      "type": "http",
      "url": "https://crawlcheck.io/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.

### 2026-11-05 (score 82, +1)

- [security] The server rewrote its instructions, which are the text every model session reads

### 2026-11-04 (score 81, 0)

- [security] The server rewrote its instructions, which are the text every model session reads

### 2026-11-03 (score 81, +1)

- [security] The server rewrote its instructions, which are the text every model session reads

### 2026-11-02 (score 80, 0)

- [security] The server rewrote its instructions, which are the text every model session reads

### 2026-11-01 (score 80, +1)

- [security] The server rewrote its instructions, which are the text every model session reads

### 2026-10-31 (score 79, 0)

- [security] The server rewrote its instructions, which are the text every model session reads

### 2026-10-30 (score 79, 0)

- [security] The server rewrote its instructions, which are the text every model session reads

### 2026-10-29 (score 79, +1)

No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (25)

### `preflight` (~209 tokens)

Call BEFORE reading, citing, connecting to or transacting with a domain. Returns a signed decision: allow, warn, require_confirmation, block or unsupported, with every step that led there and the resolve answer it was made from. Pass your crawler token as agent so robots.txt is checked for you. A policy can only make the decision stricter. Do not proceed on block; ask the user on require_confirmation.

Input parameters:

- `action` (string): What you are about to do (default read)
- `agent` (string): Your crawler user-agent token, e.g. GPTBot
- `domain` (string, required): Bare domain, e.g. example.com
- `policy` (object): max_age_hours, on_warn (warn|require_confirmation|block), require_entity, human_approval[], allow[], deny[]
- `template` (string): safe_citation, safe_data_retrieval, safe_api_connect, safe_mcp_tool, safe_commerce, safe_oauth or support_escalation

### `best_source` (~157 tokens)

Call when choosing WHICH business or site to cite, recommend or call. Give domains (2-10 candidate sites you found) or trade and city for a measured market. Returns the candidates ranked by what CrawlCheck verified (preflight decision for cite, security and threat listing, domain age, uptime, published facts that directories agree with, FTC phone complaints) with reasons for and against each; sites that share one phone number or near-identical homepage text are collapsed into one network so a copycat cannot outrank the business it copies. Signed.

Input parameters:

- `city` (string): e.g. Denver
- `domains` (array): Candidate sites, bare domains, up to 10
- `trade` (string): e.g. tree service

### `resolve_domain` (~155 tokens)

Call before fetching from, citing, connecting to or transacting with a domain. Returns one signed answer: what the domain claims, what it actually serves each crawler identity, who controls it, what CrawlCheck's published rules decide for each action (a decision for read, cite, connect and transact, with its doubts and maximum age), what changed, and the evidence behind each part, marked declared, observed or not_measured with its time. There is no overall score. A domain never measured gets a just-in-time partial answer within about 2 seconds that names every part not read in time, and is queued for the full scan; nothing is guessed.

Input parameters:

- `domain` (string, required): Bare domain, e.g. example.com

### `field_check` (~289 tokens)

Call before using a phone number, address, opening hours or service area you hold for a business. One signed verdict per business field. field=phone|address|hours|service_area and value= the value you hold. phone: matches, former_value (with dates), not_this_business (the site never published it and another publisher is named with the page that prints it), or not_published. address: matches, same_street_other_city, former_value, not_this_business, not_published or nothing_declared. hours: a week (Mo-Fr 08:00-17:00) gives matches or differs per day; a moment (Sa 10:00) gives open or closed. service_area: declared, not_declared or nothing_declared. Built from the business's own site (and its Business Profile for the licence holder), its dated fact history, CrawlCheck's scans of other sites, and for an unknown number a web search whose cited pages are read plus a YellowPages reverse lookup.

Input parameters:

- `domain` (string, required): Bare domain of the business, e.g. example.com
- `field` (string, required)
- `value` (string, required): The value you hold: a 10-digit number, a street address, a week (Mo-Fr 08:00-17:00) or a moment (Sa 10:00), or a place name

### `scan_domain` (~73 tokens)

Scan a public domain as several crawler identities and return the graded record: grade, AI-visibility score, per-section scores, findings with evidence, and whether the origin refused CrawlCheck. One scan takes 5-15 seconds.

Input parameters:

- `domain` (string, required): A bare domain such as example.com, or a full URL

### `list_verified_capabilities` (~111 tokens)

What a domain declares agents can do (OpenAPI operations, MCP tools, A2A skills, API catalog entries), each classed by safety (read_only_public up to financial), and which ones CrawlCheck actually called and confirmed - plus every mismatch between declaration and behaviour. Only read-only public actions are ever called; everything else says why it was not. From the latest scan on file.

Input parameters:

- `domain` (string, required)
- `verified_only` (boolean): Return only the capabilities that were confirmed

### `mcp_servers` (~77 tokens)

Which remote MCP servers the official MCP Registry lists on a domain, and what each endpoint actually answered when CrawlCheck sent the MCP handshake (initialized, auth_required, unreachable, tool count, tool-list drift). Use before selecting an MCP tool from that domain.

Input parameters:

- `domain` (string, required): Bare domain or host, e.g. example.com

### `verify_crawler_log` (~86 tokens)

Given raw web-server access-log lines, decide for each line that names a crawler (GPTBot, ClaudeBot, Googlebot, PerplexityBot...) whether the source IP falls inside that operator's published ranges. Returns verified, spoofed, or unverifiable when the operator publishes no ranges.

Input parameters:

- `lines` (string, required): Up to 200 raw log lines, newline separated

### `corpus_state` (~48 tokens)

Coverage of CrawlCheck's public dataset: how many distinct domains have been measured and how they split by platform, rendering, size, language and kind, with the strata that are still under-sampled.

### `resolve_robots` (~82 tokens)

Resolve every named answer engine, search index and training crawler against a domain's robots.txt the way a crawler does: most-specific group only, longest match, allow wins a tie. Shows when a Disallow under * does not apply to an agent with its own group.

Input parameters:

- `domain` (string, required)
- `path` (string): Path to test, default /

### `draft_llms` (~54 tokens)

Draft an llms.txt from the domain's own homepage and up to 25 declared pages, using their titles and descriptions. A draft for the owner to cut down, not a publication.

Input parameters:

- `domain` (string, required)

### `fix_robots` (~69 tokens)

The domain's served robots.txt, corrected: * group rules copied into named groups that lacked them (shadowing), a Sitemap line added when missing, a minimal replacement when the served file was HTML. Every change is listed at the top; nothing else is touched.

Input parameters:

- `domain` (string, required)

### `fix_entitymap` (~63 tokens)

A starter entitymap.json built from the domain's latest scan record: name, phone, coordinates and declared service areas as entities with SERVES relations. Fields the page never stated are marked TODO, never guessed. Needs a prior scan.

Input parameters:

- `domain` (string, required)

### `video_check` (~60 tokens)

One YouTube video against the video anchor model: metadata, chapters, captions and storyboard where observed, twelve checks each naming what it reads.

Input parameters:

- `fresh` (boolean): Bypass the six-hour cache
- `v` (string, required): Video id or URL

### `video_channel` (~70 tokens)

Every upload on a YouTube channel, read 50 at a time, sorted by views. The upload list is free; the per-check tally needs a Watch licence and is not offered here.

Input parameters:

- `handle` (string): @channel handle
- `id` (string): Channel id, if no handle

### `video_site` (~74 tokens)

The site half of video: homepage plus up to 60 sitemap pages read for YouTube embeds, facades and page-builder widgets, VideoObject nodes and their required properties, and - with a handle - how many of the channel's videos the site carries.

Input parameters:

- `domain` (string, required)
- `handle` (string)

### `registry_lookup` (~145 tokens)

Whether a domain is in CrawlCheck's registry and what it serves: llms.txt, agents.md, a media kit at /.well-known/media-kit.json, a reciprocity-tested entity graph, an AI access policy that names crawlers, and agent-callable surfaces. With no domain, returns the shelf counts across every measured site. A row exists because a fetch produced it; nothing here is self-reported and no payment moves a shelf.

Input parameters:

- `domain` (string): A bare domain. Omit for the corpus-wide shelf counts.
- `shelf` (string): Filter the list to one shelf: llms, agents, mediakit, entity, aipolicy, agentapi

### `crawler_path` (~173 tokens)

Where each crawler's path into a domain dies, as an observed data flow: edge decision, robots.txt as a file, robots.txt rules, then the page, JSON-LD, sitemap, llms.txt and entitymap.json it reached. Give agent (e.g. ClaudeBot, GPTBot, googlebot) for one identity's path and a one-line answer; omit it for every identity plus the stores and breaks. Uses the latest record on file, or scans first when there is none (fresh=true forces a scan). The answer-engine output is drawn but never measured.

Input parameters:

- `agent` (string): Identity id or label, e.g. claudebot, GPTBot, Googlebot
- `domain` (string, required)
- `fresh` (boolean): Scan now instead of using the record on file

### `public_counts` (~57 tokens)

The figures CrawlCheck quotes about itself, read from the source: sites_measured, domains_in_corpus, crawler_visits (a rolling window), sections, sections_scored, findings_published, guides_published, with an at timestamp.

### `telemetry` (~37 tokens)

Verified-crawler traffic observed at crawlcheck.io itself: which named agents arrived, how many claims were confirmed against operator ranges, how many were forged.

### `fix_mostly_code` (~118 tokens)

A fix plan for PAGE_IS_MOSTLY_CODE: the homepage's measured bytes by category, the largest blocks with what to do with each, ordered steps with the text ratio after each, and the step at which the detector would stop firing - or, when moving code cannot clear it, how much markup to cut or text to add. Give domain (fetched now) or id (a stored scan).

Input parameters:

- `domain` (string)
- `id` (string): Report id: plan from the stored scan instead of fetching

### `fix_stale_cache` (~99 tokens)

A fix plan for STALE_CACHE_SERVED: the homepage fetched now, its Age, the cache layers that name themselves in the headers in purge order (innermost first), the HTML lifetime each response declares, a fresh-read comparison, and whether a purge clears the finding and keeps it cleared.

Input parameters:

- `domain` (string)
- `id` (string): Report id; the page is still fetched now, because cache state is live

### `fix_machine_chain` (~106 tokens)

A fix plan for MACHINE_CHAIN_HEAVY: the files a crawler reads before the page and the 404s absent agent files return, then measured reductions (llms.txt to an index, a sitemap index, robots.txt comments and duplicate groups, minified JSON, short 404s) with the chain size after each and the step at which the detector stops firing.

Input parameters:

- `domain` (string): Uses the latest scan on file
- `id` (string): Report id

### `explain_finding` (~168 tokens)

Why CrawlCheck decided a finding: the rule and its revision, the exact fetches it compared (identity, status, bytes, sha256), when the condition held on the site, and a Merkle proof that the decision is inside the signed manifest. Give id (a d1: decision or f1: finding id from a report) or domain for its top finding. Other findings, and lookups by code, need a licence for that domain (send it in x-crawlcheck-key).

Input parameters:

- `code` (string): Finding code (licence only)
- `domain` (string): Bare domain; alone it explains the top finding
- `id` (string): d1: decision id, f1: finding id, or report id
- `path` (string)

### `machine_record` (~87 tokens)

The unified machine record for one observation: subject, grade, findings (the top one in full without a licence), capabilities with verification, and the evidence roots, manifest and verifier links that let anyone check it offline. Give id (report, d1:, f1: or manifest sha256) or domain for the latest.

Input parameters:

- `domain` (string)
- `id` (string)

## Diagnostics

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

## Score history

- 2026-11-05: 82
- 2026-11-04: 81
- 2026-11-03: 81
- 2026-11-02: 80
- 2026-11-01: 80
- 2026-10-31: 79
- 2026-10-30: 79
- 2026-10-29: 79
- 2026-10-28: 78
- 2026-10-27: 78
- 2026-10-26: 77
- 2026-10-25: 77
- 2026-10-24: 76
- 2026-10-23: 76
- 2026-10-22: 75
- 2026-10-21: 75
- 2026-10-20: 74
- 2026-10-19: 74
- 2026-10-18: 73
- 2026-10-17: 73
- 2026-10-16: 73
- 2026-10-15: 72
- 2026-10-14: 72
- 2026-10-13: 72
- 2026-10-12: 71
- 2026-10-11: 71

## Common questions

### What is the CrawlCheck MCP server?

CrawlCheck is an MCP server listed in the public MCP registry as io.github.emmanuelorta/crawlcheck. Verification layer for the agentic web: a signed answer about any site before an agent acts. This page covers its hosted endpoint (https://crawlcheck.io/mcp).

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

CrawlCheck scores 82 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 CrawlCheck MCP server expose?

CrawlCheck exposes 25 tools: preflight, best_source, resolve_domain, field_check, scan_domain, and 20 more. Their descriptions and schemas cost roughly 2,667 tokens of context every time the server is loaded.

### Does the CrawlCheck MCP server require authentication?

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

### Is the CrawlCheck MCP server still maintained?

CrawlCheck 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://crawlcheck.io/mcp
- Repository: https://github.com/emmanuelorta/crawlcheck-core
- Website: https://crawlcheck.io/
- Changelog RSS feed: https://verifymcp.io/servers/emmanuelorta-crawlcheck/crawlcheck.xml
- Changelog JSON feed: https://verifymcp.io/servers/emmanuelorta-crawlcheck/crawlcheck.json
- HTML version of this page: https://verifymcp.io/servers/emmanuelorta-crawlcheck/crawlcheck