# DABLOCK AI Visibility Index (remote · dablock.ai)

Measured share of answer for 24 crypto and Web3 brands. An open dataset, not an audit of your site.

- Trust score: 69/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-06

## Components

- remote · `dablock.ai`: 69/100 (this document), [markdown](https://verifymcp.io/servers/ai-dablock-visibility-index/dablock.md), [page](https://verifymcp.io/servers/ai-dablock-visibility-index/dablock)

## Channel facts

- Endpoint: `https://dablock.ai/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.1`

## 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 2026-08-06.

- **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**: 66/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1177 tokens (~235/item across 5 items; 5 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 3/100
  - Stability observed for 1 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.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http ai-dablock-visibility-index https://dablock.ai/mcp
```

### Codex

```toml
[mcp_servers.ai-dablock-visibility-index]
url = "https://dablock.ai/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ai-dablock-visibility-index": {
      "type": "remote",
      "url": "https://dablock.ai/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ai-dablock-visibility-index --url https://dablock.ai/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ai-dablock-visibility-index:
    url: "https://dablock.ai/mcp"
```

### Other

```json
{
  "mcpServers": {
    "ai-dablock-visibility-index": {
      "type": "http",
      "url": "https://dablock.ai/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.

### 2026-08-06 (score 69, +11)

- [security improvement] HTTPS: unverified → pass
- [security improvement] Authorization: unverified → partial
- [security] Tool “get_brand_visibility” rewrote its description, which is the text the model reads
- [security] Tool “get_history” rewrote its description, which is the text the model reads
- [security] Tool “get_methodology” rewrote its description, which is the text the model reads
- [security] Tool “get_visibility_index” rewrote its description, which is the text the model reads
- [security] Tool “list_tracked_brands” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: pass → fail
- [functional improvement] Stability: unverified → 0.03
- [functional improvement] Tool “get_brand_visibility” now declares an output schema
- [functional improvement] Tool “get_history” now declares an output schema
- [functional improvement] Tool “get_methodology” now declares an output schema
- [functional improvement] Tool “get_visibility_index” now declares an output schema
- [functional improvement] Tool “list_tracked_brands” now declares an output schema
- [functional] First check of Tool coverage: 100
- [functional] Schema quality: good → excellent
- [cosmetic] “get_brand_visibility” reworded the description of “slug”
- [cosmetic] Tool “get_brand_visibility” changed its title: Look up one brand
- [cosmetic] Tool “get_history” changed its title: Full measurement time series
- [cosmetic] Tool “get_methodology” changed its title: How the index is measured
- [cosmetic] Tool “get_visibility_index” changed its title: DABLOCK AI Visibility Index — full table
- [cosmetic] Tool “list_tracked_brands” changed its title: List tracked brands and slugs

### 2026-08-05 (score 58)

First indexed and scored.

## MCP tools (5)

### `get_visibility_index` (~240 tokens)

DABLOCK AI Visibility Index — full table

The whole current release in one call: every tracked brand in crypto/Web3 with its rank, share of answer overall and per engine, commercial intent and quadrant. Share of answer is the percentage of a fixed panel of category buyer prompts in which an engine names the brand.

Use this when the question is about the field — who leads, who is absent, how the category looks. It is one response of roughly 8 KB for 24 brands, so prefer it over calling get_brand_visibility repeatedly.

Do NOT use it for one named brand (get_brand_visibility is the direct answer), for movement over time (get_history holds the series; a single release cannot show a trend), or to audit a website's own AI visibility — this is a measured dataset about third-party brands, not a site audit. Covers crypto/Web3 only; the sibling index at dabyte.ai covers the other niche.

Re-measured weekly, so the same call returns the same figures until the next release. Data is CC BY 4.0 and free: no key, no account, no rate limit — cite the release date and dablock.ai when quoting a number.

Output parameters:

- `engines` (array): Engines measured in this release.
- `entries` (array)
- `measured_at` (string): Date of this release, ISO 8601.
- `niche_title` (string)
- `panel_version` (integer): Prompt panel version. Figures from different versions are not comparable.

### `get_brand_visibility` (~239 tokens)

Look up one brand

One brand's standing in the current DABLOCK release: share of answer per engine, rank, quadrant, how many panel prompts name it, and which ones.

Use this when a specific brand is named. Takes a slug, not a display name — call list_tracked_brands first if you are unsure, or read the slug from get_visibility_index.

An unknown slug is not a failure to hide: the error names every valid slug, so a second attempt can succeed. A brand absent from the index has not been measured at all, which is different from a measured zero. Only crypto/Web3 brands are tracked. For the field as a whole use get_visibility_index; for this brand over time, get_history.

Re-measured weekly, so the same call returns the same figures until the next release. Data is CC BY 4.0 and free: no key, no account, no rate limit — cite the release date and dablock.ai when quoting a number.

Input parameters:

- `slug` (string, required): Brand slug, lowercase with hyphens — 'slack', 'coinbase', 'monday-com'. Not the display name.

Output parameters:

- `brand` (string): Brand name as published.
- `commercial_intent` (number): How commercially loaded the brand's category demand is.
- `engines` (array): Engines measured in this release.
- `is_client` (boolean): Whether the brand is a client of the publisher. Placement cannot be bought; this flag makes that checkable.
- `measured_at` (string): Date of this release, ISO 8601.
- `niche_title` (string)
- `panel_version` (integer): Prompt panel version. Figures from different versions are not comparable.
- `per_engine` (object): Share of answer per engine, same scale.
- `prompts` (array): Panel prompts in which the brand is named.
- `quadrant` (string): Position on visibility against commercial intent.
- `rank` (integer): Position in this release, 1 = most named.
- `slug` (string): Identifier used by get_brand_visibility.
- `visibility_score` (number): Share of answer, percent of panel prompts naming the brand.

### `list_tracked_brands` (~191 tokens)

List tracked brands and slugs

The names and slugs of every brand in the DABLOCK index — a lookup table, nothing else. No scores, no ranks.

Use it for two things: to turn a brand name into the slug get_brand_visibility needs, and to answer whether a brand is tracked at all.

Do NOT use it when you want figures — get_visibility_index returns the same brands with their full measurements in a single call, so calling this one first is a wasted round trip. Absence here means the brand is not measured, not that it scores zero. Covers crypto/Web3 only; the sibling index at dabyte.ai covers the other niche.

Re-measured weekly, so the same call returns the same figures until the next release. Data is CC BY 4.0 and free: no key, no account, no rate limit — cite the release date and dablock.ai when quoting a number.

Output parameters:

- `brands` (array)

### `get_history` (~229 tokens)

Full measurement time series

Every DABLOCK release ever published, as a series per brand: share of answer at each weekly measurement with the date and panel version it was taken under.

Use this for any question about change — is a brand rising, when did it enter the index, how volatile is the category.

Two limits decide whether an answer is honest. Figures are comparable only WITHIN a panel version: the panel is frozen between releases and a version change alters the denominator, so a difference across that boundary is not a trend. And one mention on one engine is a whole scale step, since each prompt runs once per engine per release — a movement of one step is inside the noise of a language model and should not be reported as a gain or a loss. Call get_methodology for the exact step size. For the current release alone use get_visibility_index.

Re-measured weekly, so the same call returns the same figures until the next release. Data is CC BY 4.0 and free: no key, no account, no rate limit — cite the release date and dablock.ai when quoting a number.

Output parameters:

- `measurements` (array)
- `series` (object): Per brand slug, the share of answer at each release.

### `get_methodology` (~233 tokens)

How the index is measured

The rules behind every figure this server returns: the exact prompt panel and its version, which engines were measured, how share of answer is scored and rounded, the resolution of the scale in percentage points, and the editorial firewall and ownership disclosure.

Call this before quoting a number as evidence, before comparing two releases, or whenever a user asks how the measurement was made or who publishes it. It is the only tool that tells you how much of a difference is meaningful, which is what stops a one-step wobble being reported as a movement.

It returns rules, not figures — no brand appears in the response. For figures use get_visibility_index or get_brand_visibility; for the series, get_history. The panel is public and frozen between releases, so every published number can be recomputed by a third party from the archive at https://dablock.ai/archive/.

Re-measured weekly, so the same call returns the same figures until the next release. Data is CC BY 4.0 and free: no key, no account, no rate limit — cite the release date and dablock.ai when quoting a number.

Output parameters:

- `engines` (array): Engines measured in this release.
- `license` (string)
- `measured_at` (string): Date of this release, ISO 8601.
- `niche_title` (string)
- `panel_version` (integer): Prompt panel version. Figures from different versions are not comparable.
- `prompt_panel` (array): The exact prompts, verbatim.
- `publisher` (string)
- `resolution` (string): Percentage points one mention on one engine is worth.
- `scoring` (string): How share of answer is computed.

## Diagnostics

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

## Score history

- 2026-08-06: 69
- 2026-08-05: 58

## Links

- Remote endpoint: https://dablock.ai/mcp
- Repository: https://github.com/creanlab/ai-visibility-index
- Website: https://dablock.ai/
- Changelog RSS feed: https://verifymcp.io/servers/ai-dablock-visibility-index/dablock.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-dablock-visibility-index/dablock.json
- HTML version of this page: https://verifymcp.io/servers/ai-dablock-visibility-index/dablock