# Habits prompt-injection guard (remote · habits.darmousseh.com)

Check user prompts for injection/jailbreaks; your own guard learns from your labels. Works keyless.

- Trust score: 12/100 (low)
- Change this week: −47
- Registry status: deprecated
- Liveness: degraded
- Owner verified: no
- Last scored: 2026-11-21

> **Deprecated**: this server is marked deprecated in the MCP registry. The registry records this reason: "The hosted service is retired; the endpoint no longer answers."

> **Degraded**: one or more channels of this server are currently unreachable; their trust score is decaying and will reach 0 if they stay down.

## Components

- remote · `habits.darmousseh.com`: 12/100 (this document), [markdown](https://verifymcp.io/servers/com-darmousseh-habits-guard/habits.md), [page](https://verifymcp.io/servers/com-darmousseh-habits-guard/habits)

## Channel facts

- Endpoint: `https://habits.darmousseh.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.1`

## 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 2026-11-21.

- **Endpoint Security**: 11/100
  - TLS not yet verified: we couldn't open a connection to check the certificate.
  - Authorisation not yet verified: we couldn't confirm whether this endpoint requires it.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS not yet verified: we couldn't read the response headers to check for it.
  - DNSSEC not yet verified: we couldn't validate it against a resolver.
- **Transport & Reachability**: 0/100
  - Transport check failed: declared streamable-http, but we couldn't connect to verify it.
- **Schema Quality & AI Usability**: 0/100
  - Schema not yet verified: we couldn't read the endpoint's schema, or could read only part of its tool list.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 0/100
  - Tool coverage not yet verified: we couldn't read the endpoint's tools, or could read only part of the list.
- **Tool Safety**: 0/100
  - Tool safety not yet verified: we couldn't read the endpoint's tools, or could read only part of the list.
- **Capabilities**: 0/100
  - Capabilities not yet verified: we couldn't read the endpoint's capabilities.

**Unverified: 5 categories.** Categories scored 0 because we could not verify them: 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 Habits prompt-injection guard MCP server?

Habits prompt-injection guard is a hosted endpoint at https://habits.darmousseh.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-darmousseh-habits-guard 'https://habits.darmousseh.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-darmousseh-habits-guard": {
      "url": "https://habits.darmousseh.com/mcp"
    }
  }
}
```

### VS Code

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

### Codex

```toml
[mcp_servers.com-darmousseh-habits-guard]
url = "https://habits.darmousseh.com/mcp"
```

### opencode

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

### OpenClaw

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

### Hermes

```yaml
mcp_servers:
  com-darmousseh-habits-guard:
    url: "https://habits.darmousseh.com/mcp"
```

### Netclaw

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

### Vellum

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

### Other

```json
{
  "mcpServers": {
    "com-darmousseh-habits-guard": {
      "type": "http",
      "url": "https://habits.darmousseh.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.

### 2026-11-21 (score 12, −12)

The score moved with no change recorded against any check. We would rather say so than guess.

### 2026-11-20 (score 24, −11)

The score moved with no change recorded against any check. We would rather say so than guess.

### 2026-11-19 (score 35, −12)

The score moved with no change recorded against any check. We would rather say so than guess.

### 2026-11-18 (score 47, −12)

The score moved with no change recorded against any check. We would rather say so than guess.

### 2026-11-16 (score 59, +55)

The score moved with no change recorded against any check. We would rather say so than guess.

### 2026-11-15 (score 4, −55)

- [security regression] Endpoint reachability: reachable → unreachable
- [security regression] DNSSEC: fail → unverified
- [security regression] HSTS header: fail → unverified
- [security regression] Stability: 0.07 → unverified
- [security regression] Tool safety: pass → unverified
- [security regression] TLS certificate: pass → unverified
- [security regression] Transport: pass → fail
- [security improvement] HTTPS: unverified → pass
- [security] Authorization: Authorisation not yet verified: we couldn't confirm whether this endpoint requires it.
- [functional regression] Capabilities: fail → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional] First check of Schema quality: unverified

### 2026-11-14 (score 59, +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.

### 2026-11-13 (score 58, 0)

- [functional improvement] Stability: unverified → 0.03

## MCP tools (3)

### `check_prompt` (~123 tokens)

Check a prompt for injection

Is this user-typed text a prompt injection or jailbreak (an attempt to override, hijack or extract an AI system's instructions)? Returns flagged true/false and a 0-1 score. Without a key it uses the public guard (30 checks per day per network). With a key it uses your own guard, which learns from teach_guard; the result carries a request_id. Built for user prompts; it is weak on injections hidden in tool output or documents.

Input parameters:

- `text` (string, required): the user prompt to check, up to 8,000 characters

### `teach_guard` (~99 tokens)

Teach your guard

Label one prompt for your own guard so it stops repeating a mistake (a false alarm on a normal request, or a missed injection). Needs an API key (get_free_key). About 50 of your own labels cut false alarms from 15% to 4% in our benchmark.

Input parameters:

- `injection` (boolean, required): true if it IS an injection/jailbreak, false if it is a normal request
- `text` (string, required): the prompt

### `get_free_key` (~83 tokens)

Get a free API key

Create a free Habits account and API key (no email). The key is shown once; set it as the Authorization: Bearer header for this MCP server. The free plan has a fixed $0.10/day spend cap and its own trainable injection guard.

Input parameters:

- `username` (string): optional: 2-32 of a-z 0-9 -

## Diagnostics

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

## Score history

- 2026-11-21: 12
- 2026-11-20: 24
- 2026-11-19: 35
- 2026-11-18: 47
- 2026-11-17: 59
- 2026-11-16: 59
- 2026-11-15: 4
- 2026-11-14: 59
- 2026-11-13: 58
- 2026-11-12: 58

## Common questions

### What is the Habits prompt-injection guard MCP server?

Habits prompt-injection guard is an MCP server listed in the public MCP registry as com.darmousseh/habits-guard. Check user prompts for injection/jailbreaks; your own guard learns from your labels. Works keyless. This page covers its hosted endpoint (https://habits.darmousseh.com/mcp).

### Is the Habits prompt-injection guard MCP server safe to use?

Habits prompt-injection guard scores 12 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 Habits prompt-injection guard MCP server expose?

Habits prompt-injection guard exposes 3 tools: check_prompt, teach_guard, get_free_key. Their descriptions and schemas cost roughly 305 tokens of context every time the server is loaded.

### Does the Habits prompt-injection guard MCP server require authentication?

Its publisher declares no required credentials for Habits prompt-injection guard. We have not been able to confirm that against the live endpoint, and a server can require authorisation without declaring it here.

### Is the Habits prompt-injection guard MCP server still maintained?

Habits prompt-injection guard is marked deprecated in the MCP registry. We last reached this channel on 15 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 Habits prompt-injection guard MCP server?

VerifyMCP ran 2 checks on Habits prompt-injection guard, covering HTTPS and Transport. 9 items could not be completed, a gap on our side rather than a finding about Habits prompt-injection guard: TLS certificate, Authorization, HSTS header, DNSSEC and 5 more. 5 categories score 0 for that reason, because we only credit what we can confirm. 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://habits.darmousseh.com/mcp
- Website: https://habits.darmousseh.com/
- Changelog RSS feed: https://verifymcp.io/servers/com-darmousseh-habits-guard/habits.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-darmousseh-habits-guard/habits/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/com-darmousseh-habits-guard/habits.json
- HTML version of this page: https://verifymcp.io/servers/com-darmousseh-habits-guard/habits
