# io.github.5dive-ai/5dive-mcp (npm · @5dive/mcp)

Expose the 5dive agent-fleet CLI (tasks, agents, digest) as stdio MCP tools.

- Trust score: 69/100 (medium)
- Change this week: +23
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `@5dive/mcp`: 69/100 (this document), [markdown](https://verifymcp.io/servers/5dive-ai-5dive-mcp/5dive-mcp.md), [page](https://verifymcp.io/servers/5dive-ai-5dive-mcp/5dive-mcp)

## Channel facts

- Registry: `npm`
- Package: `@5dive/mcp`
- Version: `0.1.1`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, 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 2026-08-03.

- **Supply Chain Security**: 86/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (94 of 98), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (94 of 98), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 30 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 77/100
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 407 tokens (~67/item across 6 items; 6 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 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.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add 5dive-ai-5dive-mcp -- npx -y @5dive/mcp
```

### Codex

```bash
codex mcp add 5dive-ai-5dive-mcp -- npx -y @5dive/mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "5dive-ai-5dive-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@5dive/mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add 5dive-ai-5dive-mcp --command npx --arg -y --arg @5dive/mcp
```

### Hermes

```yaml
mcp_servers:
  5dive-ai-5dive-mcp:
    command: "npx"
    args: ["-y", "@5dive/mcp"]
```

### Other

```json
{
  "mcpServers": {
    "5dive-ai-5dive-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@5dive/mcp"
      ]
    }
  }
}
```

## 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.

### 2026-08-02 (score 69, +35)

- [security regression] Provenance: fail → unverified
- [security regression] Install scripts: pass → unverified
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Malware scan: unverified → pass
- [security] Stability: Stability not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet.
- [functional regression] Capabilities: pass → unverified
- [functional regression] License: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Maintenance: pass → unverified
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Stability: unverified → 0.23
- [functional improvement] Schema quality: unverified → excellent
- [functional] First check of Schema quality: unverified
- [functional] Licence: MIT

### 2026-08-01 (score 34, +13)

- [security regression] Provenance: unverified → fail
- [security improvement] Install scripts: unverified → pass
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional improvement] License: unverified → pass
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] MCP protocol: unverified → pass
- [functional] Licence: MIT

### 2026-07-31 (score 21, −7)

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

### 2026-07-30 (score 28, −18)

- [security regression] Malware scan: pass → unverified

### 2026-07-27 (score 46)

First indexed and scored.

## MCP tools (6)

### `task_create` (~128 tokens)

Create a task in the shared 5dive task queue. Returns the new task's id (e.g. DIVE-N). Use for filing work for an agent or human on the fleet.

Input parameters:

- `assignee` (string): Agent name to assign to.
- `body` (string): Full task description / context.
- `from` (string): Who is filing the task.
- `parent` (string): Parent task id (numeric or DIVE-N) to nest under.
- `priority` (string): Task priority (default: medium).
- `title` (string, required): Short task title.

### `task_show` (~57 tokens)

Fetch full detail for one task by id (numeric or DIVE-N): status, priority, body, result, subtasks, and blockers.

Input parameters:

- `id` (string, required): Task id, e.g. 923 or DIVE-923.

### `task_list` (~77 tokens)

List tasks in the shared queue. Defaults to open tasks in priority order; filter by status or assignee.

Input parameters:

- `all` (boolean): Include closed tasks too.
- `assignee` (string): Filter by assignee agent name.
- `status` (string): Filter by status (e.g. todo, in_progress, blocked, done).

### `agent_send` (~64 tokens)

Send a message to another agent on the fleet by name (inter-agent comms). The recipient receives it in-session.

Input parameters:

- `from` (string): Sender label (optional).
- `message` (string, required): Message text to deliver.
- `name` (string, required): Recipient agent name.

### `agent_list` (~27 tokens)

List every agent on the box: name, type, channels, model, and live state.

### `digest_get` (~54 tokens)

Get the fleet's daily standup digest (activity, token burn, health). Pass window=7d for the weekly view.

Input parameters:

- `window` (string): Digest window: 1d (default) or 7d.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/5dive-ai-5dive-mcp/5dive-mcp#diagnostics

## Score history

- 2026-08-03: 69
- 2026-08-02: 69
- 2026-08-01: 34
- 2026-07-31: 21
- 2026-07-30: 28
- 2026-07-28: 46
- 2026-07-27: 46

## Links

- npm package: https://www.npmjs.com/package/@5dive/mcp
- Socket report: https://socket.dev/npm/package/@5dive/mcp
- Repository: https://github.com/5dive-ai/5dive-mcp
- Changelog RSS feed: https://verifymcp.io/servers/5dive-ai-5dive-mcp/5dive-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/5dive-ai-5dive-mcp/5dive-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/5dive-ai-5dive-mcp/5dive-mcp