# AlertsBar (remote · mcp.alerts.bar)

Domain exposures: breaches, infostealers, ULP heap, cookies. Counts and samples, free.

- Trust score: 69/100 (medium)
- Change this week: +36
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-06

## Components

- remote · `mcp.alerts.bar`: 69/100 (this document), [markdown](https://verifymcp.io/servers/bar-alerts-alertsbar/mcp.md), [page](https://verifymcp.io/servers/bar-alerts-alertsbar/mcp)

## Channel facts

- Endpoint: `https://mcp.alerts.bar/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.1.1`

## 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 2026-10-06.

- **Endpoint Security**: 74/100
  - 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 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 937 tokens (~468/item across 2 items; 2 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **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.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 2 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 3 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.

**Unverified: 1 category.** A category scored 0 because we could not verify it: authentication we do not have, an unreachable endpoint, or not enough scan history. We only credit what we can confirm.

## Install

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

AlertsBar is a hosted endpoint at https://mcp.alerts.bar/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 bar-alerts-alertsbar 'https://mcp.alerts.bar/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "bar-alerts-alertsbar": {
      "url": "https://mcp.alerts.bar/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "bar-alerts-alertsbar": {
      "type": "http",
      "url": "https://mcp.alerts.bar/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.bar-alerts-alertsbar]
url = "https://mcp.alerts.bar/mcp"
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add bar-alerts-alertsbar --url 'https://mcp.alerts.bar/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  bar-alerts-alertsbar:
    url: "https://mcp.alerts.bar/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "bar-alerts-alertsbar": {
      "Transport": "http",
      "Url": "https://mcp.alerts.bar/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add bar-alerts-alertsbar -t streamable-http -u 'https://mcp.alerts.bar/mcp'
```

### Other

```json
{
  "mcpServers": {
    "bar-alerts-alertsbar": {
      "type": "http",
      "url": "https://mcp.alerts.bar/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.

### 2026-10-06 (score 69, +36)

- [security improvement] Authorization: unverified → partial
- [security improvement] Injection markers: unverified → pass
- [security] First check of Judged manipulation: pass
- [functional regression] Schema quality: 234 → 468
- [functional regression] Schema quality: unverified → fail
- [functional improvement] Endpoint reachability: not serving MCP → reachable
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] MCP protocol: unverified → pass
- [functional] First check of Destructive annotations: pass
- [functional] First check of Tool coverage: 100
- [functional] First check of Tool coverage: 100
- [functional] This server's schema is too large to store in full, so we cannot compare its tools day to day

### 2026-09-28 (score 33, 0)

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

### 2026-09-26 (score 33, 0)

- [security regression] Endpoint reachability: reachable → not serving MCP

### 2026-09-25 (score 33, −16)

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

### 2026-09-24 (score 49, +1)

- [functional improvement] Stability: unverified → 0.03
- [functional] This server's schema is too large to store in full, so we cannot compare its tools day to day

### 2026-09-23 (score 48)

First indexed and scored.

## MCP tools (2)

### `exposure_counts_for_domain` (~334 tokens)

Credential-exposure counters for a domain. Counts only - no credential values or per-account detail. Sources: known breaches, infostealer infections, unattributed heap of ULP (Url,Login,Password) bundles, stolen cookies. All figures are INDEXATION dates, not incident dates: _month/_week mean 'newly indexed', never 'newly leaked' - the underlying leak may be years old. Windows nest (_total includes _month includes _week) - never sum them. Counters are rebuilt once daily, so figures are up to 24h old and never real-time. Repeated calls for the same input within a day return identical values - do not re-query to check for changes. Accepts a bare domain or a full URL; scheme, path, port, case and a leading www. are stripped and subdomains collapse to the registrable domain (multi-tenant hosting suffixes such as github.io are not collapsed). An IDN must already be in punycode (xn--) form. Invalid input (not a domain, an IP address) returns an error. If the domain is not in the index at all, every counter and both dates are null: that means NO DATA, not that the domain is clean - never report it as 'no exposure'. first_indexed_at and last_indexed_at give the date range of the domain's records; use last_indexed_at as the 'last updated' date for the domain. Free, no auth.

Input parameters:

- `domain` (string, required): Domain to check, e.g. example.com. A full URL is accepted and normalized.

Output parameters:

- `breaches_month` (integer|null): Indexed in last 30d. Subset of breaches_total.
- `breaches_total` (integer|null): Records from known breach incidents, indexed all time.
- `breaches_week` (integer|null): Indexed in last 7d. Subset of breaches_month.
- `cookies_month` (integer|null): Indexed in last 30d. Subset of cookies_total.
- `cookies_total` (integer|null): Stolen browser session cookies, indexed all time. Non-zero means session-hijacking risk that a password reset alone does not fix. Cookies are counted here only; they are not included in exposure_samp…
- `cookies_week` (integer|null): Indexed in last 7d. Subset of cookies_month.
- `domain` (string): Normalized domain actually queried. May differ from the input - report this one to the user.
- `first_indexed_at` (string|null): Date-time (format YYYY-MM-DD HH:MM:SS, UTC) when AlertsBar first indexed a record for this domain. Indexation date, not incident date - never say the domain was first leaked then. Null if the domain…
- `heap_staff_month` (integer|null): Indexed in last 30d. Subset of heap_staff_total.
- `heap_staff_total` (integer|null): Staff logins in unattributed heap of ULP (Url,Login,Password) bundles - no linkable breach, device or leak date. Credentials circulating in the wild.
- `heap_staff_week` (integer|null): Indexed in last 7d. Subset of heap_staff_month.
- `heap_users_month` (integer|null): Indexed in last 30d. Subset of heap_users_total.
- `heap_users_total` (integer|null): Customer logins in unattributed heap of ULP (Url,Login,Password) bundles - no linkable breach, device or leak date.
- `heap_users_week` (integer|null): Indexed in last 7d. Subset of heap_users_month.
- `last_indexed_at` (string|null): Date-time (format YYYY-MM-DD HH:MM:SS, UTC) when AlertsBar last indexed a record for this domain. This is the domain's 'last updated' date and the only reliable freshness signal - samples are random…
- `stealers_staff_month` (integer|null): Indexed in last 30d. Subset of stealers_staff_total.
- `stealers_staff_total` (integer|null): Staff logins from infostealer-infected devices, indexed all time. Implies a compromised machine, not just a leaked password. The credentials may be for any site, not only this domain's own systems.
- `stealers_staff_week` (integer|null): Indexed in last 7d. Subset of stealers_staff_month.
- `stealers_users_month` (integer|null): Indexed in last 30d. Subset of stealers_users_total.
- `stealers_users_total` (integer|null): Customer logins for this domain's site from infostealer-infected devices, indexed all time.
- `stealers_users_week` (integer|null): Indexed in last 7d. Subset of stealers_users_month.

### `exposure_samples_for_domain` (~245 tokens)

A small RANDOM sample of individual exposure records for a domain - metadata only, capped in number: up to 20 records per type (stealers_users, stealers_staff, heap_users, heap_staff, breaches). Cookies are not sampled - see cookies_* in exposure_counts_for_domain. The sample is neither the newest nor the largest nor the most severe records, and it can differ between calls; identical-looking records can repeat and because of different logins/passwords. Each record says WHICH url was affected, WHICH domain the captured login belonged to, from WHICH source type, roughly when the incident was, and when the record was indexed. It carries NO credentials: no password, no username, and the login's local part is redacted. Use exposure_counts_for_domain first for the scale of the problem and for freshness (last_indexed_at); use this only when the user asks to see concrete examples. Calling again returns another random subset, never the full set - do not call it repeatedly to collect more records.

Input parameters:

- `domain` (string, required): Domain to check, e.g. example.com. A full URL is accepted and normalized, same rules as exposure_counts_for_domain.

Output parameters:

- `domain` (string): Normalized domain actually queried. May differ from the input - report this one to the user.
- `records` (array): A random subset of up to 20 records per type, listed by indexed_at descending inside this response. NOT the newest records: a recent or old indexed_at here says nothing about the domain's overall rec…

## Diagnostics

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

## Score history

- 2026-10-06: 69
- 2026-10-04: 33
- 2026-10-03: 33
- 2026-10-02: 33
- 2026-10-01: 33
- 2026-09-30: 33
- 2026-09-29: 33
- 2026-09-28: 33
- 2026-09-27: 33
- 2026-09-26: 33
- 2026-09-25: 33
- 2026-09-24: 49
- 2026-09-23: 48

## Common questions

### What is the AlertsBar MCP server?

AlertsBar is an MCP server listed in the public MCP registry as bar.alerts/alertsbar. Domain exposures: breaches, infostealers, ULP heap, cookies. Counts and samples, free. This page covers its hosted endpoint (https://mcp.alerts.bar/mcp).

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

AlertsBar scores 69 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 AlertsBar MCP server expose?

AlertsBar exposes 2 tools: exposure_counts_for_domain, exposure_samples_for_domain. Their descriptions and schemas cost roughly 579 tokens of context every time the server is loaded.

### Does the AlertsBar MCP server require authentication?

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

### Is the AlertsBar MCP server still maintained?

AlertsBar is still listed as active in the MCP registry. We last reached this channel on 6 October 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://mcp.alerts.bar/mcp
- Website: https://www.alerts.bar/
- Changelog RSS feed: https://verifymcp.io/servers/bar-alerts-alertsbar/mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/bar-alerts-alertsbar/mcp.json
- HTML version of this page: https://verifymcp.io/servers/bar-alerts-alertsbar/mcp