# Visual Sentinel (npm · @visualsentinel/mcp-server)

Website monitoring for AI assistants: catches pages that look broken even when the site is up.

- Trust score: 72/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `visualsentinel.com`: 39/100, [markdown](https://verifymcp.io/servers/com-visualsentinel-mcp-server/api-mcp.md), [page](https://verifymcp.io/servers/com-visualsentinel-mcp-server/api-mcp)
- npm · `@visualsentinel/mcp-server`: 72/100 (this document), [markdown](https://verifymcp.io/servers/com-visualsentinel-mcp-server/visualsentinel-mcp-server.md), [page](https://verifymcp.io/servers/com-visualsentinel-mcp-server/visualsentinel-mcp-server)

## Channel facts

- Registry: `npm`
- Package: `@visualsentinel/mcp-server`
- Version: `0.2.3`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, 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 2026-11-21.

- **Supply Chain Security**: 81/100
  - No malware found by supply-chain analysis.
  - CVE check failed: a known high-severity CVE affects zod 3.25.76, a direct dependency. A fixed version is available.
  - No install/post-install scripts declared.
  - 31 of 93 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 11 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 84/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 1640 tokens (~82/item across 20 items; 17 tools + 3 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 40/100
  - Stability observed for 12 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 98/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 93% 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 17 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 18 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 Visual Sentinel MCP server?

Visual Sentinel runs locally as an npm package, launched with npx -y @visualsentinel/mcp-server. 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 com-visualsentinel-mcp-server -- npx -y @visualsentinel/mcp-server
```

### Cursor

```json
{
  "mcpServers": {
    "com-visualsentinel-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@visualsentinel/mcp-server"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-visualsentinel-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@visualsentinel/mcp-server"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add com-visualsentinel-mcp-server -- npx -y @visualsentinel/mcp-server
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-visualsentinel-mcp-server": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@visualsentinel/mcp-server"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-visualsentinel-mcp-server --command npx --arg -y --arg @visualsentinel/mcp-server
```

### Hermes

```yaml
mcp_servers:
  com-visualsentinel-mcp-server:
    command: "npx"
    args: ["-y", "@visualsentinel/mcp-server"]
```

### Netclaw

```json
{
  "McpServers": {
    "com-visualsentinel-mcp-server": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@visualsentinel/mcp-server"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-visualsentinel-mcp-server -t stdio -c npx -a -y @visualsentinel/mcp-server
```

### Other

```json
{
  "mcpServers": {
    "com-visualsentinel-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@visualsentinel/mcp-server"
      ]
    }
  }
}
```

## 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.

### 2026-11-21 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-19 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-17 (score 70, +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.

### 2026-11-14 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-12 (score 68, +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.

### 2026-11-10 (score 67, +1)

No change was recorded against any check on this day. Stability & Change Management went from 0 to 3. That category is still filling its 30-day observation window: 0 days of observed history at the previous scan, 1 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-09 (score 66)

First indexed and scored.

## MCP tools (17)

### `vs_health` (~26 tokens)

Check Visual Sentinel service health

Check whether Visual Sentinel itself is up. Returns the service health status. No authentication required.

### `vs_dns_check` (~101 tokens)

Look up DNS records

Resolve DNS records (A, AAAA, MX, NS, TXT, CNAME) for a domain using Visual Sentinel's public DNS lookup tool. No authentication required.

Input parameters:

- `domain` (string, required): Domain to resolve, e.g. example.com (without protocol).
- `recordType` (string): Optional: limit to one record type. One of: A, AAAA, MX, NS, TXT, CNAME, SOA. Default: all.

### `vs_ssl_check` (~60 tokens)

Inspect an SSL certificate

Inspect a TLS/SSL certificate for a hostname: issuer, subject, validity dates, SAN list, key algorithm, and certificate chain. No authentication required.

Input parameters:

- `domain` (string, required): Hostname to inspect, e.g. example.com (without protocol).

### `vs_speed_test` (~84 tokens)

Run a one-shot speed test

Run a one-shot Lighthouse lab test on a URL. Returns the performance score (0 to 100) plus Largest Contentful Paint, First Contentful Paint, Cumulative Layout Shift, Time to First Byte, Total Blocking Time and Speed Index (times in milliseconds). No account needed.

Input parameters:

- `url` (string, required): Full URL to test, including protocol (https://...).

### `vs_website_check` (~56 tokens)

Check a website

Quick health check for a URL: HTTP status, response time, server header, content snippet, and basic SSL state. No authentication required.

Input parameters:

- `url` (string, required): Full URL to test, including protocol (https://...).

### `vs_monitors_list` (~120 tokens)

List monitors

List monitors in the authenticated organization. Optional filters narrow by status, type, or paginate.

Input parameters:

- `limit` (integer): Items per page (default 50, max 200).
- `page` (integer): Page number (default 1).
- `status` (string): Filter: UP, DOWN, PAUSED, MAINTENANCE.
- `type` (string): Filter by monitor type: HTTP, HTTPS, KEYWORD, PING, PORT, DNS, SSL, VISUAL, CONTENT, API, GRAPHQL, WEBSOCKET.

### `vs_monitors_get` (~40 tokens)

Get a monitor

Fetch a single monitor by id, including its current status, last check, and configuration.

Input parameters:

- `id` (string, required): Monitor id (cuid).

### `vs_monitors_create` (~194 tokens)

Create a monitor

Create a new monitor. Provide at least name, url, and type. Returns the created monitor including its assigned id.

Input parameters:

- `interval` (integer): Check interval in seconds (60, 300, 600, 1800, 3600).
- `keyword` (string): Keyword to assert for KEYWORD monitors.
- `method` (string): HTTP method for HTTP/HTTPS monitors (default GET).
- `name` (string, required): Display name for the monitor.
- `port` (integer): TCP port for PORT monitors.
- `timeout` (integer): Per-check timeout in seconds (default 30).
- `type` (string, required): Monitor type: HTTP, HTTPS, KEYWORD, PING, PORT, DNS, SSL, VISUAL, CONTENT, API, GRAPHQL, WEBSOCKET.
- `url` (string, required): Full URL to monitor (or hostname for PING/PORT/DNS/SSL).

### `vs_monitors_check_now` (~43 tokens)

Run a monitor check now

Trigger an immediate check for a monitor (in addition to its scheduled cadence). Returns the freshly-collected check result.

Input parameters:

- `id` (string, required): Monitor id.

### `vs_monitors_uptime` (~242 tokens)

Get monitor uptime

Fetch the uptime percentage and time-series breakdown for a monitor. Use `window` for a preset window (24h, 7d, 30d, 90d, 365d; default 30d), supply both `from` and `to` (ISO 8601) for a custom date range, or set `all: true` for the full available history.

Input parameters:

- `all` (boolean): Return the full available history from the earliest stored data. Takes precedence over from/to and window.
- `from` (string): ISO 8601 start of a custom range (e.g. 2026-01-01T00:00:00Z). Must be supplied with `to`.
- `id` (string, required): Monitor id.
- `to` (string): ISO 8601 end of a custom range. Must be supplied with `from`.
- `window` (string): Preset window: 1h, 6h, 24h, 7d, 30d, 90d, 365d. Default 30d. Ignored when from+to or all are supplied.

### `vs_monitors_metrics_bulk` (~297 tokens)

Get bulk monitor metrics

Fetch uptime or response-time metrics for up to 100 monitors in a single request. Use `window` for a preset window (1h, 6h, 24h, 7d, 30d, 90d, 365d; default 30d), supply both `from` and `to` (ISO 8601) for a custom date range, or set `all: true` for the full available history. Returns a `monitors` object keyed by monitor id.

Input parameters:

- `all` (boolean): Return the full available history from the earliest stored data. Takes precedence over from/to and window.
- `from` (string): ISO 8601 start of a custom range (e.g. 2026-01-01T00:00:00Z). Must be supplied with `to`.
- `metric` (string, required): Metric to return: "uptime" or "response-time".
- `monitorIds` (array, required): List of monitor IDs to fetch metrics for (max 100).
- `to` (string): ISO 8601 end of a custom range. Must be supplied with `from`.
- `window` (string): Preset window: 1h, 6h, 24h, 7d, 30d, 90d, 365d. Default 30d. Ignored when from+to or all are supplied.

### `vs_incidents_list` (~78 tokens)

List incidents

List incidents for the authenticated organization. Filter by status (OPEN/RESOLVED), monitor id, or paginate.

Input parameters:

- `limit` (integer): Default 50, max 200.
- `monitorId` (string): Filter to one monitor.
- `page` (integer)
- `status` (string): OPEN or RESOLVED.

### `vs_incidents_get` (~34 tokens)

Get an incident

Fetch a single incident with its full check history and root-cause hints.

Input parameters:

- `id` (string, required): Incident id.

### `vs_alerts_list` (~82 tokens)

List alerts

List alerts for the authenticated organization. Filter by status (UNACKNOWLEDGED/ACKNOWLEDGED/RESOLVED) or paginate.

Input parameters:

- `limit` (integer): Default 50, max 200.
- `page` (integer)
- `status` (string): UNACKNOWLEDGED, ACKNOWLEDGED, or RESOLVED.

### `vs_alerts_acknowledge` (~56 tokens)

Acknowledge an alert

Acknowledge an alert by id. The acknowledgement is recorded against the account that authorised this connection.

Input parameters:

- `id` (string, required): Alert id.
- `note` (string): Optional acknowledgement note (visible in alert history).

### `vs_status_pages_list` (~21 tokens)

List status pages

List public-facing status pages owned by the authenticated organization.

### `vs_servers_list` (~38 tokens)

List servers

List servers (origins) registered in the authenticated organization.

Input parameters:

- `limit` (integer): Default 50.
- `page` (integer)

## Diagnostics

Captured diagnostic sections: Provenance, Vulnerabilities, Dependencies. The full working is on the page: https://verifymcp.io/servers/com-visualsentinel-mcp-server/visualsentinel-mcp-server#diagnostics

## Score history

- 2026-11-21: 72
- 2026-11-20: 71
- 2026-11-19: 71
- 2026-11-18: 70
- 2026-11-17: 70
- 2026-11-16: 69
- 2026-11-15: 69
- 2026-11-14: 69
- 2026-11-13: 68
- 2026-11-12: 68
- 2026-11-11: 67
- 2026-11-10: 67
- 2026-11-09: 66

## Common questions

### What is the Visual Sentinel MCP server?

Visual Sentinel is an MCP server listed in the public MCP registry as com.visualsentinel/mcp-server. Website monitoring for AI assistants: catches pages that look broken even when the site is up. This page covers its npm package (@visualsentinel/mcp-server).

### Is the Visual Sentinel MCP server safe to use?

Visual Sentinel scores 72 out of 100 on VerifyMCP. We recorded 1 known advisory against it as of 21 November 2026. It declares no install or post-install scripts. 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 Visual Sentinel MCP server expose?

Visual Sentinel exposes 17 tools: vs_health, vs_dns_check, vs_ssl_check, vs_speed_test, vs_website_check, and 12 more. Their descriptions and schemas cost roughly 1,572 tokens of context every time the server is loaded.

### Is the Visual Sentinel MCP server still maintained?

Visual Sentinel is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the Visual Sentinel MCP server under?

Visual Sentinel declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

### What did VerifyMCP test on the Visual Sentinel MCP server?

VerifyMCP ran 16 checks on Visual Sentinel, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- npm package: https://www.npmjs.com/package/@visualsentinel/mcp-server
- Socket report: https://socket.dev/npm/package/@visualsentinel/mcp-server
- Repository: https://github.com/VisualSentinel/mcp-server
- Website: https://visualsentinel.com/mcp
- Changelog RSS feed: https://verifymcp.io/servers/com-visualsentinel-mcp-server/visualsentinel-mcp-server.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-visualsentinel-mcp-server/visualsentinel-mcp-server/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/com-visualsentinel-mcp-server/visualsentinel-mcp-server.json
- HTML version of this page: https://verifymcp.io/servers/com-visualsentinel-mcp-server/visualsentinel-mcp-server
