# LoginLlama (remote · loginllama.app)

Ask questions about your login security data: risk scores, blocked logins, Tor, VPN and bot traffic.

- Trust score: 65/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-26

## Components

- remote · `loginllama.app`: 65/100 (this document), [markdown](https://verifymcp.io/servers/joshghent-loginllama/api-v1-mcp.md), [page](https://verifymcp.io/servers/joshghent-loginllama/api-v1-mcp)

## Channel facts

- Endpoint: `https://loginllama.app/api/v1/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## 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 2026-10-26.

- **Endpoint Security**: 63/100
  - 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 5 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.
  - 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**: 65/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 767 tokens (~153/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**: 23/100
  - Stability observed for 7 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.
  - We read all 5 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 20/100
  - Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28.

## Install

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

LoginLlama is a hosted endpoint at https://loginllama.app/api/v1/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 joshghent-loginllama 'https://loginllama.app/api/v1/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "joshghent-loginllama": {
      "url": "https://loginllama.app/api/v1/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "joshghent-loginllama": {
      "type": "http",
      "url": "https://loginllama.app/api/v1/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.joshghent-loginllama]
url = "https://loginllama.app/api/v1/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "joshghent-loginllama": {
      "type": "remote",
      "url": "https://loginllama.app/api/v1/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add joshghent-loginllama --url 'https://loginllama.app/api/v1/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  joshghent-loginllama:
    url: "https://loginllama.app/api/v1/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "joshghent-loginllama": {
      "Transport": "http",
      "Url": "https://loginllama.app/api/v1/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add joshghent-loginllama -t streamable-http -u 'https://loginllama.app/api/v1/mcp'
```

### Other

```json
{
  "mcpServers": {
    "joshghent-loginllama": {
      "type": "http",
      "url": "https://loginllama.app/api/v1/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.

### 2026-10-25 (score 65, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-23 (score 64, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-21 (score 63, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-20 (score 62, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-10-19 (score 62)

First indexed and scored.

## MCP tools (5)

### `get_login_stats` (~169 tokens)

Overall login security summary for your team: total checks, average risk score, high-risk count, blocked/failed logins, and bot/Tor/VPN counts. Supports filtering by browser, OS, country, device, user and time window.

Input parameters:

- `browser` (string): Filter by browser, case-insensitive partial match e.g. "chrome".
- `country` (string): Filter by country e.g. "United States".
- `days` (number): Look back this many days (default 30). Omit for all time.
- `device` (string): Filter by device e.g. "iphone".
- `identity_key` (string): Filter to a single user identifier (email, user id, etc).
- `os` (string): Filter by operating system e.g. "windows".

### `get_average_risk_score` (~156 tokens)

Average login risk score (0-10) across matching logins. Use the filters to answer questions like "what is my average login risk score for the chrome browser".

Input parameters:

- `browser` (string): Filter by browser, case-insensitive partial match e.g. "chrome".
- `country` (string): Filter by country e.g. "United States".
- `days` (number): Look back this many days (default 30). Omit for all time.
- `device` (string): Filter by device e.g. "iphone".
- `identity_key` (string): Filter to a single user identifier (email, user id, etc).
- `os` (string): Filter by operating system e.g. "windows".

### `get_login_breakdown` (~191 tokens)

Group logins by a dimension (browser, os, device, country, or status) and return counts, average risk score and high-risk counts per group. Good for "which browser has the highest risk".

Input parameters:

- `browser` (string): Filter by browser, case-insensitive partial match e.g. "chrome".
- `country` (string): Filter by country e.g. "United States".
- `days` (number): Look back this many days (default 30). Omit for all time.
- `device` (string): Filter by device e.g. "iphone".
- `dimension` (string, required): The attribute to group by.
- `identity_key` (string): Filter to a single user identifier (email, user id, etc).
- `os` (string): Filter by operating system e.g. "windows".
- `top_n` (number): Max groups to return (default 20).

### `get_recent_logins` (~186 tokens)

List the most recent login checks (newest first) with risk score, status, location and device. Supports the same filters.

Input parameters:

- `browser` (string): Filter by browser, case-insensitive partial match e.g. "chrome".
- `country` (string): Filter by country e.g. "United States".
- `days` (number): Look back this many days (default 30). Omit for all time.
- `device` (string): Filter by device e.g. "iphone".
- `identity_key` (string): Filter to a single user identifier (email, user id, etc).
- `limit` (number): How many to return (default 25, max 100).
- `os` (string): Filter by operating system e.g. "windows".
- `status` (string): Filter by status, e.g. "valid" or "invalid".

### `get_account_usage` (~28 tokens)

Your LoginLlama account usage: remaining API credits for production and staging, and plan name.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/joshghent-loginllama/api-v1-mcp#diagnostics

## Score history

- 2026-10-26: 65
- 2026-10-25: 65
- 2026-10-24: 64
- 2026-10-23: 64
- 2026-10-22: 63
- 2026-10-21: 63
- 2026-10-20: 62
- 2026-10-19: 62

## Common questions

### What is the LoginLlama MCP server?

LoginLlama is an MCP server listed in the public MCP registry as io.github.joshghent/loginllama. Ask questions about your login security data: risk scores, blocked logins, Tor, VPN and bot traffic. This page covers its hosted endpoint (https://loginllama.app/api/v1/mcp).

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

LoginLlama scores 65 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 LoginLlama MCP server expose?

LoginLlama exposes 5 tools: get_login_stats, get_average_risk_score, get_login_breakdown, get_recent_logins, get_account_usage. Their descriptions and schemas cost roughly 730 tokens of context every time the server is loaded.

### Does the LoginLlama MCP server require authentication?

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

### Is the LoginLlama MCP server still maintained?

LoginLlama is still listed as active in the MCP registry. We last reached this channel on 26 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://loginllama.app/api/v1/mcp
- Authorisation metadata: https://loginllama.app/.well-known/oauth-protected-resource/api/v1/mcp
- Website: https://loginllama.app/docs
- Changelog RSS feed: https://verifymcp.io/servers/joshghent-loginllama/api-v1-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/joshghent-loginllama/api-v1-mcp.json
- HTML version of this page: https://verifymcp.io/servers/joshghent-loginllama/api-v1-mcp