# net.agentutil/think-mcp (npm · @agentutil/think-mcp)

Intent security pre-flight checks for autonomous AI agents.

- Trust score: 59/100 (low)
- Change this week: +19
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `@agentutil/think-mcp`: 59/100 (this document), [markdown](https://verifymcp.io/servers/net-agentutil-think-mcp/agentutil-think-mcp.md), [page](https://verifymcp.io/servers/net-agentutil-think-mcp/agentutil-think-mcp)

## Channel facts

- Registry: `npm`
- Package: `@agentutil/think-mcp`
- Version: `1.0.0`
- 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**: 87/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (95 of 99), 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 (95 of 99), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 19/100
  - Repository check failed: no source repository is declared.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 155 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 71/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 253 tokens (~63/item across 4 items; 4 tools + 0 resources), lean.
  - 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**: 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.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### Claude

```bash
claude mcp add net-agentutil-think-mcp -- npx -y @agentutil/think-mcp
```

### Codex

```bash
codex mcp add net-agentutil-think-mcp -- npx -y @agentutil/think-mcp
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add net-agentutil-think-mcp --command npx --arg -y --arg @agentutil/think-mcp
```

### Hermes

```yaml
mcp_servers:
  net-agentutil-think-mcp:
    command: "npx"
    args: ["-y", "@agentutil/think-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "net-agentutil-think-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@agentutil/think-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 59, +7)

- [security improvement] Known CVEs: unverified → partial
- [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] Tool coverage: 100 → unverified
- [functional regression] Capabilities: pass → unverified
- [functional improvement] Dependency health: unverified → partial

### 2026-08-01 (score 52, −10)

- [security regression] Known CVEs: partial → unverified
- [functional regression] Dependency health: partial → unverified

### 2026-07-31 (score 62, +40)

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

### 2026-07-30 (score 22, −18)

- [functional regression] Tool coverage: 100 → unverified
- [functional improvement] Dependency health: unverified → partial
- [functional] First check of Schema quality: unverified

### 2026-07-27 (score 40)

First indexed and scored.

## MCP tools (4)

### `check_intent` (~100 tokens)

Pre-flight safety check before an autonomous agent executes an action. Returns risk level, risk factors, and a checklist of safety considerations.

Input parameters:

- `action` (string, required): Short action identifier (e.g. delete_records, send_email)
- `context` (object): Key-value pairs of additional context for conditional checks
- `description` (string, required): Natural language description of what the agent is about to do
- `domain` (string): Business domain for targeted checks

### `expand_intent` (~58 tokens)

Surface implied requirements from a human instruction that an autonomous agent might miss. Returns categorized requirements with confidence scores.

Input parameters:

- `domain` (string): Business domain for more targeted requirements
- `instruction` (string, required): The instruction the agent received from a human

### `review_action` (~68 tokens)

Post-action verification checklist after an autonomous agent completes an action. Returns verification items to confirm the action was safe and correct.

Input parameters:

- `action_completed` (string, required): What action was just completed
- `description` (string, required): Natural language description of what was done
- `domain` (string): Business domain

### `list_actions` (~27 tokens)

List all action types with safety checks, grouped by domain. Free endpoint — no payment required.

## Diagnostics

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

## Score history

- 2026-08-03: 59
- 2026-08-02: 59
- 2026-08-01: 52
- 2026-07-31: 62
- 2026-07-30: 22
- 2026-07-29: 40
- 2026-07-28: 40
- 2026-07-27: 40

## Links

- npm package: https://www.npmjs.com/package/@agentutil/think-mcp
- Socket report: https://socket.dev/npm/package/@agentutil/think-mcp
- Changelog RSS feed: https://verifymcp.io/servers/net-agentutil-think-mcp/agentutil-think-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/net-agentutil-think-mcp/agentutil-think-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/net-agentutil-think-mcp/agentutil-think-mcp