# Wardzo (remote · wardzo.com)

Scan and monitor websites for leaked keys, exposed files, security headers, SEO issues and uptime.

- Trust score: 78/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `wardzo.com`: 38/100, [markdown](https://verifymcp.io/servers/com-wardzo-wardzo/mcp-account.md), [page](https://verifymcp.io/servers/com-wardzo-wardzo/mcp-account)
- remote · `wardzo.com`: 78/100 (this document), [markdown](https://verifymcp.io/servers/com-wardzo-wardzo/wardzo.md), [page](https://verifymcp.io/servers/com-wardzo-wardzo/wardzo)

## Channel facts

- Endpoint: `https://wardzo.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.2.0`

## 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 2026-11-21.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (remove_endpoint).
  - 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**: 75/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1435 tokens (~119/item across 12 items; 12 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**: 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.
  - All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 13 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 Wardzo MCP server?

Wardzo is a hosted endpoint at https://wardzo.com/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 com-wardzo-wardzo 'https://wardzo.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-wardzo-wardzo": {
      "url": "https://wardzo.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-wardzo-wardzo": {
      "type": "http",
      "url": "https://wardzo.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-wardzo-wardzo]
url = "https://wardzo.com/mcp"
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add com-wardzo-wardzo --url 'https://wardzo.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-wardzo-wardzo:
    url: "https://wardzo.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-wardzo-wardzo": {
      "Transport": "http",
      "Url": "https://wardzo.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-wardzo-wardzo -t streamable-http -u 'https://wardzo.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-wardzo-wardzo": {
      "type": "http",
      "url": "https://wardzo.com/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.

### 2026-11-20 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 77 to 80. That category is still filling its 30-day observation window: 23 days of observed history at the previous scan, 24 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-19 (score 77, 0)

- [security] Tool “get_new_findings” rewrote its description, which is the text the model reads
- [cosmetic] “explain_issue” reworded the description of “issue_id”

### 2026-11-17 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 67 to 70. That category is still filling its 30-day observation window: 20 days of observed history at the previous scan, 21 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-15 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 60 to 63. That category is still filling its 30-day observation window: 18 days of observed history at the previous scan, 19 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-13 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-11 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-09 (score 73, +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.

### 2026-11-07 (score 72, +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.

## MCP tools (12)

### `scan_site` (~75 tokens)

Scan a website

Run a passive outside-in Wardzo scan of a public website (security, SEO health, uptime) and return the score, issues and report URL. Waits up to ~45 seconds for the result. Works without an API key (rate limited).

Input parameters:

- `url` (string, required): Website URL or domain, e.g. example.com

### `get_report` (~50 tokens)

Get a scan report

Get the result of a Wardzo scan by its id (from scan_site, recheck_site or a wardzo.com/r/<id> link).

Input parameters:

- `id` (string, required): Scan id or report URL

### `list_sites` (~29 tokens)

List monitored sites

List the websites monitored in your Wardzo account with their latest score, open issue counts and uptime status.

### `add_site` (~45 tokens)

Add a site to monitoring

Start monitoring a website: it is scanned now, then re-scanned on your plan schedule, with uptime checks and email alerts.

Input parameters:

- `url` (string, required): Website URL or domain

### `get_site_status` (~64 tokens)

Get site status

Latest score (with change since the previous scan), open issues by severity, top issues, uptime (24h and 7d) and what changed in the last scan, for one of your monitored sites.

Input parameters:

- `site` (string, required): Site id, domain or URL

### `list_issues` (~64 tokens)

List open issues

List open issues from the latest scan of one of your sites, most severe first. Each issue has an issue_id for explain_issue.

Input parameters:

- `severity` (string): Minimum severity to include (default: low)
- `site` (string, required): Site id, domain or URL

### `get_new_findings` (~267 tokens)

Get new findings since last check

Get the findings Wardzo detected on your monitored sites since this connection last checked (background re-scans, re-checks and new sites), newest last, and mark them as seen for this connection. A finding that stays open across scans is reported once, not every scan. The first call on a new connection returns every open finding. Each item has an issue_id for explain_issue, a status (open, or resolved if it was already fixed by the next scan) and evidence (sensitive values redacted). Use mark_seen=false to peek without marking, or since (ISO timestamp) to list findings first seen after a time (does not move the marker). Filtering by site is also a peek.

Input parameters:

- `limit` (integer): Maximum findings to return (default 50). If more are waiting, call again.
- `mark_seen` (boolean): Mark the returned findings as seen for this connection (default true)
- `since` (string): ISO 8601 timestamp, e.g. 2026-10-27T08:00:00Z. Returns findings first seen after it, ignoring and not moving the last-seen marker.
- `site` (string): Only this site (id, domain or URL). Peek only: does not mark anything as seen.

### `explain_issue` (~102 tokens)

Explain an issue and how to fix it

Explain why an issue matters and give step-by-step fix instructions (with Next.js, Vercel, Netlify, Nginx, Apache, Cloudflare and WordPress snippets where relevant) that an AI coding agent can apply, plus how to verify.

Input parameters:

- `issue_id` (string, required): issue_id from list_issues/scan_site (e.g. "AbC123xyz:hsts_missing") or a check name (e.g. "hsts_missing")

### `recheck_site` (~54 tokens)

Re-scan one of your sites

Run a fresh scan of one of your monitored sites (e.g. after deploying a fix) and report what changed. Waits up to ~45 seconds.

Input parameters:

- `site` (string, required): Site id, domain or URL

### `list_endpoints` (~59 tokens)

List endpoint checks

List the endpoint checks (GET/HEAD monitors for specific URLs such as /api/health) on one of your sites, with their current status, last HTTP status and response time.

Input parameters:

- `site` (string, required): Site id, domain or URL

### `add_endpoint` (~219 tokens)

Add an endpoint check

Monitor a specific URL on one of your verified sites (for example an API health route, login or checkout page) with a GET or HEAD request on a schedule. The domain must be verified first, and the URL must not include a query string. Optionally require an exact HTTP status, a text snippet in the response, and a maximum response time. You get an email alert when it fails twice in a row and when it recovers. Wardzo never submits forms or sends request bodies.

Input parameters:

- `expect_keyword` (string): Text that must appear in the response body (GET only)
- `expect_status` (integer): Exact expected HTTP status (default: any 2xx or 3xx)
- `max_ms` (integer): Fail if the response takes longer than this many milliseconds
- `method` (string): HTTP method (default GET)
- `site` (string, required): Site id, domain or URL of one of your monitored sites
- `url` (string, required): Full URL on that site, or a path like "/api/health"

### `remove_endpoint` (~42 tokens)

Remove an endpoint check

Stop monitoring one endpoint check and delete its history. Use list_endpoints to find the endpoint_id.

Input parameters:

- `endpoint_id` (integer, required): endpoint_id from list_endpoints

## Diagnostics

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

## Score history

- 2026-11-21: 78
- 2026-11-20: 78
- 2026-11-19: 77
- 2026-11-18: 77
- 2026-11-17: 77
- 2026-11-16: 76
- 2026-11-15: 76
- 2026-11-14: 75
- 2026-11-13: 75
- 2026-11-12: 74
- 2026-11-11: 74
- 2026-11-10: 73
- 2026-11-09: 73
- 2026-11-08: 72
- 2026-11-07: 72
- 2026-11-06: 71
- 2026-11-05: 71
- 2026-11-04: 70
- 2026-11-03: 70
- 2026-11-02: 70
- 2026-11-01: 69
- 2026-10-31: 69
- 2026-10-30: 68
- 2026-10-29: 68
- 2026-10-28: 67
- 2026-10-27: 67

## Common questions

### What is the Wardzo MCP server?

Wardzo is an MCP server listed in the public MCP registry as com.wardzo/wardzo. Scan and monitor websites for leaked keys, exposed files, security headers, SEO issues and uptime. This page covers its hosted endpoint (https://wardzo.com/mcp).

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

Wardzo scores 78 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 Wardzo MCP server expose?

Wardzo exposes 12 tools: scan_site, get_report, list_sites, add_site, get_site_status, and 7 more. Their descriptions and schemas cost roughly 1,070 tokens of context every time the server is loaded.

### Does the Wardzo MCP server require authentication?

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

### Is the Wardzo MCP server still maintained?

Wardzo 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 did VerifyMCP test on the Wardzo MCP server?

VerifyMCP ran 13 checks on Wardzo, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://wardzo.com/mcp
- Website: https://wardzo.com/mcp-server
- Changelog RSS feed: https://verifymcp.io/servers/com-wardzo-wardzo/wardzo.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-wardzo-wardzo/wardzo/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/com-wardzo-wardzo/wardzo.json
- HTML version of this page: https://verifymcp.io/servers/com-wardzo-wardzo/wardzo
