# Vivere (remote · vivere.dev)

Know when cron jobs and AI agents stop running: create monitors and check in from your agent.

- Trust score: 80/100 (high trust)
- Change this week: +44
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-23

## Components

- remote · `vivere.dev`: 80/100 (this document), [markdown](https://verifymcp.io/servers/dev-vivere-monitors/vivere.md), [page](https://verifymcp.io/servers/dev-vivere-monitors/vivere)

## Channel facts

- Endpoint: `https://vivere.dev/mcp`
- Transports: `streamable-http`
- Auth: `required`
- 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 2026-09-23.

- **Endpoint Security**: 89/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, but the challenge carries no valid RFC 9728 metadata, so a client cannot discover where to get a token.
  - 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**: 82/100
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 760 tokens (~108/item across 7 items; 7 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 20/100
  - Stability observed for 6 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 7 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 8 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

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

Vivere is a hosted endpoint at https://vivere.dev/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 dev-vivere-monitors 'https://vivere.dev/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "dev-vivere-monitors": {
      "url": "https://vivere.dev/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "dev-vivere-monitors": {
      "type": "http",
      "url": "https://vivere.dev/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.dev-vivere-monitors]
url = "https://vivere.dev/mcp"
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add dev-vivere-monitors --url 'https://vivere.dev/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  dev-vivere-monitors:
    url: "https://vivere.dev/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "dev-vivere-monitors": {
      "Transport": "http",
      "Url": "https://vivere.dev/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add dev-vivere-monitors -t streamable-http -u 'https://vivere.dev/mcp'
```

### Other

```json
{
  "mcpServers": {
    "dev-vivere-monitors": {
      "type": "http",
      "url": "https://vivere.dev/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.

### 2026-09-23 (score 80, +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.

### 2026-09-21 (score 79, +1)

- [functional] Server version: 676d51c → 8ce479a

### 2026-09-20 (score 78, 0)

- [functional] Server version: 79f381c → 676d51c

### 2026-09-19 (score 78, +1)

- [functional] Server version: dd64554 → 79f381c

### 2026-09-18 (score 77, 0)

- [functional improvement] Stability: unverified → 0.03
- [functional] Server version: 82389ad → dd64554

### 2026-09-17 (score 77, +41)

- [security improvement] Transport: unverified → pass
- [security improvement] Injection markers: unverified → pass
- [security] First check of Judged manipulation: pass
- [security] Authorization: Authorisation is enforced on tool calls, but the challenge carries no valid RFC 9728 metadata, so a client cannot discover where to get a token.
- [functional regression] MCP protocol: unverified → fail
- [functional improvement] Tool coverage: unverified → 100
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: excellent
- [functional] First check of Destructive annotations: pass
- [functional] First check of Schema quality: pass
- [functional] First check of Tool coverage: 100

### 2026-09-13 (score 36)

First indexed and scored.

## MCP tools (7)

### `list_pages` (~51 tokens)

List pages

List the pages this account can see: its own, then pages other accounts share with it, each with the access it has there (owner, editor or viewer) and how many monitors are on it and down.

### `list_monitors` (~67 tokens)

List monitors

List the monitors on every page this account can see, or on one page, with status, page and access. Monitors on a page shared to view have no id; address them by page_id and slug.

Input parameters:

- `page_id` (integer): Only this page (from list_pages)

### `get_monitor` (~82 tokens)

Get monitor

Get one monitor by id, including its ping URL for heartbeat monitors, or by page_id and slug, which also works on a page shared to view.

Input parameters:

- `id` (string): Monitor id, for monitors this account owns or edits
- `page_id` (integer): Page id, with slug
- `slug` (string): Monitor slug, with page_id

### `create_monitor` (~294 tokens)

Create monitor

Create a heartbeat monitor (default) or an HTTP check on the account's first page or on page_id, which may be a page shared with this account as editor. Returns the monitor and, for heartbeats, the ping URL to call after each run.

Input parameters:

- `cron` (string): Heartbeat alternative to period: five-field cron expression, e.g. '0 2 * * *'.
- `grace` (string): Heartbeat: how late a check-in may be before alerting, e.g. 15m. Default 15m.
- `interval` (string): HTTP check: how often to request it, e.g. 5m.
- `kind` (string): heartbeat (the job pings us) or http (we request a URL)
- `name` (string, required): Human name, e.g. 'nightly report agent'
- `page_id` (integer): Page to put it on (from list_pages). Default: the account's first page.
- `period` (string): Heartbeat: expected time between successful check-ins, e.g. 30m, 1h, 1d. Default 1h.
- `tags` (string): Optional space-separated tags.
- `timezone` (string): IANA timezone for the cron expression, e.g. Asia/Seoul. Default UTC.
- `url` (string): HTTP check: the public URL to request.

### `check_in` (~100 tokens)

Check in

Report on a heartbeat monitor: 'success' after a completed run (resets the deadline), 'start' when a run begins, 'fail' when it failed. Include a short message; it is kept as the run log.

Input parameters:

- `message` (string): Optional summary or error text to store with the run
- `monitor_id` (string, required): Monitor id (the last path segment of the ping URL)
- `status` (string): Default success

### `pause_monitor` (~32 tokens)

Pause monitor

Pause a monitor so it stops alerting until resumed or pinged again.

Input parameters:

- `id` (string, required): Monitor id

### `resume_monitor` (~22 tokens)

Resume monitor

Resume a paused monitor.

Input parameters:

- `id` (string, required): Monitor id

## Diagnostics

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

## Score history

- 2026-09-23: 80
- 2026-09-22: 79
- 2026-09-21: 79
- 2026-09-20: 78
- 2026-09-19: 78
- 2026-09-18: 77
- 2026-09-17: 77
- 2026-09-16: 36
- 2026-09-15: 36
- 2026-09-14: 36
- 2026-09-13: 36

## Common questions

### What is the Vivere MCP server?

Vivere is an MCP server listed in the public MCP registry as dev.vivere/monitors. Know when cron jobs and AI agents stop running: create monitors and check in from your agent. This page covers its hosted endpoint (https://vivere.dev/mcp).

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

Vivere scores 80 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 Vivere MCP server expose?

Vivere exposes 7 tools: list_pages, list_monitors, get_monitor, create_monitor, check_in, and 2 more. Their descriptions and schemas cost roughly 648 tokens of context every time the server is loaded.

### Does the Vivere MCP server require authentication?

Yes. Vivere asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

### Is the Vivere MCP server still maintained?

Vivere is still listed as active in the MCP registry. We last reached this channel on 23 September 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://vivere.dev/mcp
- Authorisation metadata: https://vivere.dev/.well-known/oauth-protected-resource/mcp
- Website: https://vivere.dev/docs/mcp
- Changelog RSS feed: https://verifymcp.io/servers/dev-vivere-monitors/vivere.xml
- Changelog JSON feed: https://verifymcp.io/servers/dev-vivere-monitors/vivere.json
- HTML version of this page: https://verifymcp.io/servers/dev-vivere-monitors/vivere