# The Poliety (npm · poliety-mcp)

AI news for agents: editions, change feeds, integrity proofs, and governed events with evidence.

- Trust score: 65/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-20

## Components

- npm · `poliety-mcp`: 65/100 (this document), [markdown](https://verifymcp.io/servers/dburks-svg-poliety/poliety-mcp.md), [page](https://verifymcp.io/servers/dburks-svg-poliety/poliety-mcp)

## Channel facts

- Registry: `npm`
- Package: `poliety-mcp`
- Version: `1.3.0`
- 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 2026-08-20.

- **Supply Chain Security**: 96/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 3 of 5 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 19/100
  - Repository check failed: the declared repository URL returned HTTP 404.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 8 days ago).
  - Security-disclosure policy not yet verified: we couldn't inspect the source repository.
- **Schema Quality & AI Usability**: 82/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 813 tokens (~116/item across 7 items; 7 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 33/100
  - Stability observed for 10 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**: 20/100
  - Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add dburks-svg-poliety -- npx -y poliety-mcp
```

### Codex

```bash
codex mcp add dburks-svg-poliety -- npx -y poliety-mcp
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add dburks-svg-poliety --command npx --arg -y --arg poliety-mcp
```

### Hermes

```yaml
mcp_servers:
  dburks-svg-poliety:
    command: "npx"
    args: ["-y", "poliety-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "dburks-svg-poliety": {
      "command": "npx",
      "args": [
        "-y",
        "poliety-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.

### 2026-08-19 (score 65, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-18 (score 64, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-15 (score 63, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-13 (score 62, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-12 (score 61, +16)

- [security improvement] Malware scan: unverified → pass
- [functional regression] Schema quality: pass → fail
- [functional] Package version: 1.2.0 → 1.3.0

### 2026-08-11 (score 45, −13)

- [security regression] Malware scan: pass → unverified
- [functional regression] Schema quality: 94 → 111
- [functional improvement] Stability: unverified → 0.03
- [functional] Schema quality: good → excellent
- [functional] Package version: 1.0.0 → 1.2.0
- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-08-10 (score 58)

First indexed and scored.

## MCP tools (7)

### `poliety_latest` (~68 tokens)

Get today's AI news briefing from The Poliety: the lead story, briefs, and scored wire items. Returns the current edition as structured JSON. No API key required: without one this reads the free public edition; with one it reads the paid API's copy enriched with firstSeenAt timestamps.

### `poliety_changes` (~187 tokens)

Get what changed since your last check: new stories, score changes, corrections. Pass the cursor from a previous response to receive only new changes, or use 'since' with an ISO 8601 timestamp. On first call with no cursor or since, returns a starting cursor for future delta queries.

Input parameters:

- `change` (string): Filter by change type.
- `cursor` (string): Opaque cursor from a previous poliety_changes response.
- `kind` (string): Filter to wire items or editorial briefs.
- `limit` (integer): Maximum results (default 200).
- `minScore` (number): Minimum score threshold (wire items are scored 0-100).
- `section` (string): Filter to a section (e.g. 'ai', 'startups').
- `since` (string): ISO 8601 timestamp. Alternative to cursor; returns changes since this time.

### `poliety_integrity` (~59 tokens)

Verify The Poliety's integrity chain: an append-only hash chain proving past editions have not been rewritten. Returns the chain head, root, length, and a witness recipe you can run to independently verify the current edition. No API key required.

### `poliety_events` (~182 tokens)

Get canonical events: governed, provenance-backed, hash-chained records of material changes in the AI and software ecosystem (status transitions, SDK releases, pricing and spec changes). Pass the next_cursor from a previous response as 'since' to receive only newer events. No API key required.

Input parameters:

- `entity` (string): Filter by entity id (e.g. 'anthropic', 'openai', 'nodejs').
- `limit` (integer): Maximum results (default 100).
- `min_materiality` (number): Only events at or above this materiality (0 to 1).
- `since` (string): Opaque cursor from a previous poliety_events response; omit to walk from the start of the chain.
- `type` (string): Filter by event type (e.g. 'sdk.released', 'status.degraded', 'pricing.changed').

### `poliety_event_evidence` (~103 tokens)

Inspect one event's full evidence package to decide whether it is trustworthy enough to act on: epistemic status and confidence with rationale, sources by authority, the complete Bench tribunal receipt (verdict, constitution hash, challenger findings, defender rebuttals, oracle reasoning), integrity hashes with links to the free published files, and full provenance. Requires an API key.

Input parameters:

- `event_id` (string, required): The evt_ id of the event, from poliety_events.

### `poliety_event_history` (~84 tokens)

Get one event's supersession lineage, oldest first: what was believed at each point, at what confidence, and what corrected it. Later entries supersede, never overwrite, so the record of an earlier belief survives its correction. Requires an API key.

Input parameters:

- `event_id` (string, required): The evt_ id of any event in the lineage, from poliety_events.

### `poliety_ask` (~130 tokens)

Ask The Poliety's concierge a question about the service itself: coverage (what dates the archive holds), capabilities (endpoints, integrity verification, tools), and tiers (what is free, what the key buys). Answers are grounded in Poliety's published docs and are non-canonical; the canonical_urls field in the response lists the citable sources. Not for news content (use poliety_latest or poliety_changes). No API key required; a key raises the rate limit.

Input parameters:

- `question` (string, required): A plain-language question about The Poliety service, up to 2000 characters.

## Diagnostics

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

## Score history

- 2026-08-20: 65
- 2026-08-19: 65
- 2026-08-18: 64
- 2026-08-17: 63
- 2026-08-16: 63
- 2026-08-15: 63
- 2026-08-14: 62
- 2026-08-13: 62
- 2026-08-12: 61
- 2026-08-11: 45
- 2026-08-10: 58

## Links

- npm package: https://www.npmjs.com/package/poliety-mcp
- Socket report: https://socket.dev/npm/package/poliety-mcp
- Changelog RSS feed: https://verifymcp.io/servers/dburks-svg-poliety/poliety-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/dburks-svg-poliety/poliety-mcp.json
- HTML version of this page: https://verifymcp.io/servers/dburks-svg-poliety/poliety-mcp