# Sandbox Timer (remote · timer.cloudforbots.com)

Flags idle agent sandboxes (E2B, Vercel, Daytona, Modal), shows idle cost, returns kill calls.

- Trust score: 62/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-16

## Components

- remote · `timer.cloudforbots.com`: 62/100 (this document), [markdown](https://verifymcp.io/servers/com-botrecipe-timer/timer.md), [page](https://verifymcp.io/servers/com-botrecipe-timer/timer)

## Channel facts

- Endpoint: `https://timer.cloudforbots.com/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 2026-10-16.

- **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**: 61/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 749 tokens (~149/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**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 87/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 62% of tool parameters carry a description.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "track_sessions" implies "send" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 6 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 Sandbox Timer MCP server?

Sandbox Timer is a hosted endpoint at https://timer.cloudforbots.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-botrecipe-timer 'https://timer.cloudforbots.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-botrecipe-timer": {
      "url": "https://timer.cloudforbots.com/mcp"
    }
  }
}
```

### VS Code

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

### Codex

```toml
[mcp_servers.com-botrecipe-timer]
url = "https://timer.cloudforbots.com/mcp"
```

### opencode

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

### OpenClaw

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

### Hermes

```yaml
mcp_servers:
  com-botrecipe-timer:
    url: "https://timer.cloudforbots.com/mcp"
```

### Netclaw

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

### Vellum

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

### Other

```json
{
  "mcpServers": {
    "com-botrecipe-timer": {
      "type": "http",
      "url": "https://timer.cloudforbots.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.

### 2026-10-16 (score 62)

First indexed and scored.

## MCP tools (5)

### `track_sessions` (~295 tokens)

Send your agent's running sandbox sessions (up to 200; call it on a heartbeat, e.g. every 5 minutes) and get back which are idle past your threshold or over their max lifetime, the dollars idle time has cost at the hourly rates you pass, and what to do. Pro acts: returns a ready-to-run kill call per idle sandbox for its provider (E2B kill, Vercel Sandbox stop, Daytona stop, Modal terminate) and POSTs one alert per sandbox to your webhook. Free watch-only returns would_kill and sends nothing. We never hold provider keys and never kill anything ourselves: your agent runs the call with its own key.

Input parameters:

- `alert_webhook` (string): https URL Pro posts the idle alert (with the kill call) to.
- `fleet` (string): A stable name for this group of sandboxes, e.g. "my-agent". State and rules are kept per fleet.
- `idle_minutes` (integer): Idle minutes before a sandbox counts as idle. Default 15 (or your saved Pro rule).
- `max_lifetime_minutes` (integer): Optional: flag sandboxes running longer than this, idle or not.
- `rates_per_hour` (object): Optional default USD per hour by provider, e.g. {"e2b": 0.17}. Your own numbers; per-session rate_per_hour wins.
- `sessions` (array, required)

### `idle_report` (~103 tokens)

Which sandboxes were flagged idle and what idle time cost, per provider, from what track_sessions has seen. Without an API key pass fleet. With a key: every fleet on it. Free shows 7 days, Pro 30.

Input parameters:

- `days` (integer): 1-30 (free max 7).
- `fleet` (string): A stable name for this group of sandboxes, e.g. "my-agent". State and rules are kept per fleet.

### `set_idle_rules` (~131 tokens)

Pro: save the rules track_sessions applies to a fleet: idle_minutes threshold, max_lifetime_minutes, default rates_per_hour by provider, and alert_webhook. Free returns a preview of the rules and saves nothing (pass the same values on each track_sessions call instead).

Input parameters:

- `alert_webhook` (string)
- `fleet` (string): A stable name for this group of sandboxes, e.g. "my-agent". State and rules are kept per fleet.
- `idle_minutes` (integer)
- `max_lifetime_minutes` (integer)
- `rates_per_hour` (object)

### `weekly_report` (~61 tokens)

Plain-English summary of the last 7 days: sandboxes watched, how many sat idle, dollars idle time cost at your rates, kill calls returned (Pro) or that would have been (free). Read-only; sends nothing. Needs a free API key.

### `usage_and_upgrade` (~37 tokens)

Show today's usage for your key or IP and the $9/month upgrade link. Free tier: 500 calls/day. Not metered.

## Diagnostics

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

## Score history

- 2026-10-16: 62

## Common questions

### What is the Sandbox Timer MCP server?

Sandbox Timer is an MCP server listed in the public MCP registry as com.botrecipe/timer. Flags idle agent sandboxes (E2B, Vercel, Daytona, Modal), shows idle cost, returns kill calls. This page covers its hosted endpoint (https://timer.cloudforbots.com/mcp).

### Is the Sandbox Timer MCP server safe to use?

Sandbox Timer scores 62 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 Sandbox Timer MCP server expose?

Sandbox Timer exposes 5 tools: track_sessions, idle_report, set_idle_rules, weekly_report, usage_and_upgrade. Their descriptions and schemas cost roughly 627 tokens of context every time the server is loaded.

### Does the Sandbox Timer MCP server require authentication?

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

### Is the Sandbox Timer MCP server still maintained?

Sandbox Timer is still listed as active in the MCP registry. We last reached this channel on 16 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://timer.cloudforbots.com/mcp
- Website: https://timer.cloudforbots.com/
- Changelog RSS feed: https://verifymcp.io/servers/com-botrecipe-timer/timer.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-botrecipe-timer/timer.json
- HTML version of this page: https://verifymcp.io/servers/com-botrecipe-timer/timer