# AI Incident Law (npm · ai-incident-law)

Public-record corpus of AI litigation, regulation, and enforcement, anchored to EveryAILaw.

- Trust score: 64/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `ai-incident-law`: 64/100 (this document), [markdown](https://verifymcp.io/servers/snapsynapse-ai-incident-law/ai-incident-law.md), [page](https://verifymcp.io/servers/snapsynapse-ai-incident-law/ai-incident-law)

## Channel facts

- Registry: `npm`
- Package: `ai-incident-law`
- Version: `0.2.1`
- 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**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - No production dependencies, so there is no dependency health to assess.
- **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 8 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 70/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 525 tokens (~65/item across 8 items; 8 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**: 20/100
  - Spec-recency check failed: implements MCP spec 2024-11-05; 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 snapsynapse-ai-incident-law -- npx -y ai-incident-law
```

### Codex

```bash
codex mcp add snapsynapse-ai-incident-law -- npx -y ai-incident-law
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add snapsynapse-ai-incident-law --command npx --arg -y --arg ai-incident-law
```

### Hermes

```yaml
mcp_servers:
  snapsynapse-ai-incident-law:
    command: "npx"
    args: ["-y", "ai-incident-law"]
```

### Other

```json
{
  "mcpServers": {
    "snapsynapse-ai-incident-law": {
      "command": "npx",
      "args": [
        "-y",
        "ai-incident-law"
      ]
    }
  }
}
```

## 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 64, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-08-01 (score 49, −12)

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

### 2026-07-27 (score 61, +32)

- [functional improvement] Tool coverage: unverified → 100
- [functional] First check of Schema quality: pass
- [functional] First check of Tool coverage: 100
- [functional] First check of Schema quality: good
- [functional] First check of Schema quality: fail

### 2026-07-26 (score 29)

First indexed and scored.

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

## MCP tools (8)

### `list_datasets` (~23 tokens)

Summarize the available AI Incident Law dataset buckets and record counts.

### `list_records` (~150 tokens)

List compact AI incident law records, optionally filtered by dataset, domain, type, jurisdiction, status, source quality, or review flag.

Input parameters:

- `dataset` (string): Dataset bucket, such as included, review, or global.
- `domain` (string): Domain/category substring filter.
- `error_type` (string): Error or event type substring filter.
- `filing_status` (string): Outcome or procedural posture substring filter.
- `jurisdiction` (string): Jurisdiction, country, or authority substring filter.
- `limit` (number): Maximum records to return. Default 25.
- `needs_review` (string): Review flag, usually yes or no.
- `source_quality` (string): Source quality substring filter.

### `get_record` (~42 tokens)

Get one full AI Incident Law source record by error_id or candidate_id.

Input parameters:

- `id` (string, required): Record ID, such as AIEL-2024-001.

### `search_records` (~63 tokens)

Search across record titles, descriptions, parties, jurisdictions, tags, and source metadata.

Input parameters:

- `dataset` (string): Optional dataset bucket filter.
- `limit` (number): Maximum matches to return. Default 10.
- `query` (string, required): Case-insensitive search query.

### `get_staleness_report` (~117 tokens)

Report record verification decay: records ranked oldest-verified first, with per-bucket counts. Use to find matters overdue for re-verification before relying on them.

Input parameters:

- `as_of` (string): Optional ISO date (YYYY-MM-DD) to age records against. When omitted, days_stale is not computed and records are returned sorted by verification date only.
- `dataset` (string): Optional dataset bucket filter, such as included, review, or global.
- `limit` (number): Maximum records to return. Default 25.

### `list_authorities` (~22 tokens)

List Obligation-First authority records generated from included public matters.

### `get_authority` (~43 tokens)

Get a generated Obligation-First authority record by authority ID.

Input parameters:

- `id` (string, required): Authority ID, such as british-columbia-civil-resolution-tribunal.

### `get_obligation_first_record` (~65 tokens)

Get a generated Obligation-First proceeding, allegation, determination, or authority record by kind and ID.

Input parameters:

- `id` (string, required): Generated Obligation-First record ID.
- `kind` (string, required): Record kind: proceedings, allegations, determinations, or authorities.

## Diagnostics

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

## Score history

- 2026-08-03: 64
- 2026-08-02: 64
- 2026-08-01: 49
- 2026-07-31: 61
- 2026-07-29: 61
- 2026-07-28: 61
- 2026-07-27: 61
- 2026-07-26: 29

## Links

- npm package: https://www.npmjs.com/package/ai-incident-law
- Socket report: https://socket.dev/npm/package/ai-incident-law
- Repository: https://github.com/snapsynapse/ai-incident-law
- Website: https://aiincidentlaw.org/
- Changelog RSS feed: https://verifymcp.io/servers/snapsynapse-ai-incident-law/ai-incident-law/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/snapsynapse-ai-incident-law/ai-incident-law/changelog.json
- HTML version of this page: https://verifymcp.io/servers/snapsynapse-ai-incident-law/ai-incident-law