# CertScore.ai — Light mode (remote · mcp.certscore.ai)

No-account public website privacy risk scans with 20 new scans/day and free recent-result reuse.

- Trust score: 66/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `mcp.certscore.ai`: 66/100 (this document), [markdown](https://verifymcp.io/servers/ai-certscore-mcp-light/mcp-light.md), [page](https://verifymcp.io/servers/ai-certscore-mcp-light/mcp-light)

## Channel facts

- Endpoint: `https://mcp.certscore.ai/mcp/light`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.2.12`

## 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 2026-08-03.

- **Endpoint Security**: 57/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 2 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - 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**: 71/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 363 tokens (~121/item across 3 items; 3 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 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**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http ai-certscore-mcp-light https://mcp.certscore.ai/mcp/light
```

### Codex

```toml
[mcp_servers.ai-certscore-mcp-light]
url = "https://mcp.certscore.ai/mcp/light"
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add ai-certscore-mcp-light --url https://mcp.certscore.ai/mcp/light --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ai-certscore-mcp-light:
    url: "https://mcp.certscore.ai/mcp/light"
```

### Other

```json
{
  "mcpServers": {
    "ai-certscore-mcp-light": {
      "type": "http",
      "url": "https://mcp.certscore.ai/mcp/light"
    }
  }
}
```

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.

### 2026-08-03 (score 66, +28)

- [security] Authorization: Authorisation not fully verified: no authorisation is required to call this server, and 2 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
- [functional regression] Schema quality: unverified → fail
- [functional improvement] Schema quality: unverified → good
- [functional improvement] Schema quality: unverified → pass
- [functional improvement] Tool coverage: unverified → 100
- [functional] Stability: fail → 0.27
- [functional] New tool “get_scan_status”
- [functional] New tool “get_scan_bundle”
- [functional] New tool “scan_site”

### 2026-08-02 (score 38, −27)

- [security regression] Stability: 0.20 → fail
- [security regression] A breaking change shipped without a version bump: still 0.2.12
- [security regression] Tool “scan_site” was removed
- [security regression] Tool “get_scan_bundle” was removed
- [security regression] Tool “get_scan_status” was removed
- [security] Authorization: Authorisation not fully verified: no authorisation is required to connect, but we couldn't read the tool list to see what that exposes.
- [functional regression] Schema quality: fail → unverified
- [functional regression] Schema quality: good → unverified
- [functional regression] Schema quality: pass → unverified
- [functional regression] Tool coverage: 100 → unverified

### 2026-07-31 (score 65, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 65, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-29 (score 64, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-27 (score 63, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 62)

First indexed and scored.

## MCP tools (3)

### `scan_site` (~184 tokens)

Scan site

Recommended first call. Starts or reuses a public-web scan, reports freshness and anonymous quota decisions, and waits up to 45 seconds by default. If still running, use get_scan_status; otherwise use get_scan_bundle. Completed no-go scans retain completed_limited status and reason-specific guidance.

Input parameters:

- `freshness` (string): Use latest to reuse recent scans or refresh to request a new scan when eligible.
- `maxWaitSeconds` (integer): Maximum time to wait before returning the still-running job. Defaults to 45 seconds; never turns an active scan into an error.
- `scanFrom` (string): Optional scan execution context for newly queued scans.
- `url` (string, required): Public URL or domain to scan.
- `waitForCompletion` (boolean): Wait for a completed scan resource in this tool call. Defaults to true. Set false only for an explicitly asynchronous workflow.

Output parameters:

- `completedAt` (string|null)
- `domain` (string|null)
- `jobId` (string)
- `noGo` (object)
- `resultDisposition` (string)
- `scanFrom` (string)
- `scanId` (string|null)
- `scanTimeSeconds` (number|null)
- `startedAt` (string|null)
- `status` (string)
- `type` (string)

### `get_scan_status` (~81 tokens)

Get CertScore Pulse scan status

Retrieve terminal status, including completed_limited no-go disposition and reason-specific guidance. Pass jobId only before a stable scanId is available.

Input parameters:

- `jobId` (string): Pulse job ID for a just-created scan that has not yet returned a scanId.
- `scanId` (string): Preferred stable CertScore scan ID for API v2 scan status.

Output parameters:

- `completedAt` (string|null)
- `domain` (string|null)
- `error` (object)
- `jobId` (string)
- `noGo` (object)
- `resultDisposition` (string)
- `scanId` (string|null)
- `scanTimeSeconds` (number|null)
- `scan_id` (string|null)
- `startedAt` (string|null)
- `status` (string)
- `type` (string)

### `get_scan_bundle` (~98 tokens)

Get compact CertScore scan bundle

Recommended second call after scan_site. Returns the canonical scan state, compact report summary, findings, bounded evidence summary, and pre-consent inventory in one agent-friendly response.

Input parameters:

- `maxFindings` (integer): Maximum compact findings to return. Defaults to 20.
- `maxPreConsentRows` (integer): Maximum pre-consent inventory rows to return. Defaults to 20.
- `scanId` (string, required): Stable CertScore scan ID.

Output parameters:

- `disclaimer` (string|null)
- `evidenceSummary`
- `findings` (array)
- `links` (object)
- `noGo`
- `preConsentCookiesTrackers`
- `recommendedNextTool` (string|null)
- `resultDisposition`
- `scan` (object)
- `scanId` (string)
- `status` (string)
- `summary`
- `type` (string)

## Diagnostics

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

## Score history

- 2026-08-03: 66
- 2026-08-02: 38
- 2026-08-01: 65
- 2026-07-31: 65
- 2026-07-30: 65
- 2026-07-29: 64
- 2026-07-28: 63
- 2026-07-27: 63
- 2026-07-26: 62

## Links

- Remote endpoint: https://mcp.certscore.ai/mcp/light
- Repository: https://github.com/ergoveritas1-alt/certscore.ai
- Website: https://certscore.ai/mcp/light
- Changelog RSS feed: https://verifymcp.io/servers/ai-certscore-mcp-light/mcp-light/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-certscore-mcp-light/mcp-light/changelog.json
- HTML version of this page: https://verifymcp.io/servers/ai-certscore-mcp-light/mcp-light