# Pure Report — Neutral News (remote · pure.report)

Neutral, bias-scored news for AI agents: compare left/right media-bias framing, fact-check receipts.

- Trust score: 68/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `pure.report`: 68/100 (this document), [markdown](https://verifymcp.io/servers/report-pure-news/pure.md), [page](https://verifymcp.io/servers/report-pure-news/pure)

## Channel facts

- Endpoint: `https://pure.report/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.2`

## 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 2026-08-03.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 7 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - 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**: 68/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1316 tokens (~164/item across 8 items; 8 tools + 0 resources), over budget; trim descriptions and params.
  - 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.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http report-pure-news https://pure.report/mcp
```

### Codex

```toml
[mcp_servers.report-pure-news]
url = "https://pure.report/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "report-pure-news": {
      "type": "remote",
      "url": "https://pure.report/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add report-pure-news --url https://pure.report/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  report-pure-news:
    url: "https://pure.report/mcp"
```

### Other

```json
{
  "mcpServers": {
    "report-pure-news": {
      "type": "http",
      "url": "https://pure.report/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.

### 2026-08-03 (score 68, 0)

- [functional regression] Schema quality: 135 → 164
- [cosmetic] “submit_feedback” added an optional parameter “category”
- [cosmetic] “about_pure_report” added an optional parameter “event_slug”
- [cosmetic] “about_pure_report” added an optional parameter “report_body”
- [cosmetic] “about_pure_report” added an optional parameter “report_kind”
- [cosmetic] “about_pure_report” added an optional parameter “report_subject”
- [cosmetic] “search_news” added an optional parameter “offset”
- [cosmetic] “search_news” added an optional parameter “published_after”
- [cosmetic] “search_news” added an optional parameter “published_before”
- [cosmetic] “about_pure_report” added an optional parameter “article_id”
- [cosmetic] “submit_feedback” reworded the description of “body”
- [cosmetic] “submit_feedback” reworded the description of “kind”
- [cosmetic] “submit_feedback” made “kind” optional

### 2026-08-02 (score 68, 0)

- [functional regression] Schema quality: 122 → 135
- [functional] New tool “submit_feedback”
- [functional] New tool “check_feedback”
- [cosmetic] “search_news” reworded the description of “limit”

### 2026-07-31 (score 68, +1)

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

### 2026-07-30 (score 67, 0)

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

### 2026-07-29 (score 67, +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.

### 2026-07-28 (score 66, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-27 (score 65, 0)

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

### 2026-07-26 (score 65)

First indexed and scored.

## MCP tools (8)

### `search_news` (~292 tokens)

Search neutral news

Search Pure Report's neutral, bias-scored news. Returns articles rewritten to remove loaded language; bias_score (0-100) rates the ORIGINAL source reporting before neutralization (0 = wire-neutral, 100 = advocacy), NOT the returned rewrite, which is neutral by design. Each result also lists the event(s) it belongs to — pass an event slug to get_event for the neutral writeup or compare_coverage for cross-outlet framing. Ranked by relevance and recency.

Input parameters:

- `limit` (integer): Max results to RETURN, 1-40 (default 15). Does not affect total_matches, which always reports how many articles matched.
- `offset` (integer): Skip this many matches — page through results beyond the 40-row limit. The response echoes offset/returned/next_offset; next_offset is null on the last page.
- `published_after` (string): Only articles published on/after this date. 'YYYY-MM-DD' or full ISO. Use with published_before to bound a period, e.g. coverage during June.
- `published_before` (string): Only articles published on/before this date. 'YYYY-MM-DD' or full ISO.
- `query` (string, required): Keywords or phrase, e.g. "Iran sanctions" or "2026 election".
- `topic` (string): Optional topic-slug filter. An unrecognized value searches all topics and returns a warning.

Output parameters:

- `applied_topic` (string|null)
- `next_offset` (integer|null)
- `offset` (integer)
- `query` (string)
- `result_composition` (object): Factual description of what the returned set is ABOUT. Search is lexical, so every query term appears in every result; this reports whether a term is the SUBJECT (title/entities/lede) or only a body…
- `results` (array)
- `returned` (integer)
- `total_matches` (integer): TOTAL articles matching the query, independent of `limit` — not the number returned. len(results) < total_matches means more exist.
- `warning` (string)

### `trending_events` (~90 tokens)

Trending news events

List the news events with the most current coverage activity. Each event clusters many outlets' articles about one story and includes has_account (boolean): true means get_event returns a full verification-gated writeup, false means only the coverage census is available yet. Returns slugs to pass to get_event / compare_coverage.

Input parameters:

- `limit` (integer): Max events, 1-25 (default 10).

Output parameters:

- `events` (array)

### `get_event` (~110 tokens)

Neutral event writeup

Get the full neutral writeup of one news event by slug: a verification-gated account (lede, what-we-know bullets with verbatim source receipts, single-source attributed items) plus a coverage census (how many outlets by political lean, earliest report). If no gated account exists yet, the coverage census is still returned.

Input parameters:

- `slug` (string, required): Event slug from trending_events or a search_news result, e.g. "tyler-robinson-trial-for-charlie-kirk-murder".

Output parameters:

- `account` (object|null)
- `account_note` (string|null)
- `article_count` (integer|null)
- `coverage` (object)
- `coverage_report` (object|null)
- `first_seen` (string|null)
- `name` (string|null)
- `slug` (string)
- `status` (string|null)
- `url` (string)

### `compare_coverage` (~81 tokens)

Compare outlet framing

Show how outlets across the political spectrum framed one event: a per-outlet bias-score spectrum and, where they editorialized, the verbatim framing quotes grouped by left/center/right. The core 'compare the coverage' view — use it to detect slant and consensus.

Input parameters:

- `slug` (string, required): Event slug from trending_events or a search_news result.

Output parameters:

- `framing_spectrum` (object|null)
- `how_each_side_framed_it` (object|null)
- `name` (string|null)
- `slug` (string)
- `url` (string)

### `get_article` (~60 tokens)

Get article

Fetch one article by id: neutral rewritten title + body, a bias_score for the ORIGINAL source (not the rewrite), source, extracted entities, and the events it belongs to.

Input parameters:

- `article_id` (integer, required): Numeric article id (from search_news results).

Output parameters:

- `bias_score` (number|null)
- `content` (string|null)
- `entities` (object|array|null)
- `events` (array)
- `id` (integer)
- `published_at` (string|null)
- `source_name` (string|null)
- `source_url` (string|null)
- `summary` (string|null)
- `title` (string|null)
- `url` (string)

### `about_pure_report` (~153 tokens)

About & methodology

How Pure Report works — the bias scale, neutralization method, the two-gate verification for event accounts, lean labeling, coverage scope (topic list), and the support contact. Call this to cite the source or explain its methodology to a user.

Input parameters:

- `article_id` (integer): Optional context for the report.
- `event_slug` (string): Optional context for the report.
- `report_body` (string): Optional. The detail needed to act.
- `report_kind` (string): Optional, defaults to bug.
- `report_subject` (string): Optional. Providing this (with report_body) files feedback and returns a ref under "filed" — use only if submit_feedback is missing from your tools.

Output parameters:

- `bias_scale` (string)
- `coverage_scope` (object)
- `filed` (object|null)
- `freshness` (string)
- `lean_labeling` (string)
- `name` (string)
- `neutralization` (string)
- `reporting_problems` (string)
- `reporting_problems_if_submit_feedback_is_missing` (string)
- `support` (string)
- `verification_gate` (string)
- `website` (string)
- `what_it_is` (string)

### `submit_feedback` (~263 tokens)

Send feedback to the operator

Report a problem or request to Pure Report's operator and get a tracking ref back. Use this when the data looks wrong — a bias score or outlet lean that doesn't match the source, an event cluster mixing unrelated stories, a missing neutral writeup, a broken article — or to ask a methodology question or request a capability. Include the article_id or event_slug you were looking at; that context is what makes a report actionable. A human reads these: replies take time and are not guaranteed. Call check_feedback with the returned ref to read the reply.

Input parameters:

- `article_id` (integer): Optional article the report concerns.
- `body` (string, required): The detail needed to act: what you expected, what you got, and how to reproduce it. Max 12000 chars.
- `category` (string): bug = broken or erroring; dx = developer-experience friction; data_error = wrong/miscategorised data; data_gap = missing coverage or field; feature = a capability request; question = methodology or u…
- `event_slug` (string): Optional event slug the report concerns.
- `kind` (string): DEPRECATED alias for category; still accepted.
- `subject` (string, required): One line, max 200 chars.

Output parameters:

- `how_to_check` (string)
- `message` (string)
- `ref` (string)
- `status` (string)

### `check_feedback` (~106 tokens)

Check a feedback reply

Look up feedback you filed with submit_feedback, using the ref it returned (e.g. PR-7F3K2Q). Returns the current status (open, answered, closed) and the operator's reply once one exists. Replies are written by a human and are not immediate — poll sparingly, on the order of hours or days, not seconds.

Input parameters:

- `ref` (string, required): The ref from submit_feedback, e.g. 'PR-7F3K2Q'.

Output parameters:

- `kind` (string)
- `message` (string)
- `ref` (string)
- `replied_at` (string|null)
- `reply` (string|null)
- `status` (string)
- `subject` (string)
- `submitted_at` (string|null)

## Diagnostics

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

## Score history

- 2026-08-03: 68
- 2026-08-02: 68
- 2026-08-01: 68
- 2026-07-31: 68
- 2026-07-30: 67
- 2026-07-29: 67
- 2026-07-28: 66
- 2026-07-27: 65
- 2026-07-26: 65

## Links

- Remote endpoint: https://pure.report/mcp
- Website: https://pure.report/for-agents
- Changelog RSS feed: https://verifymcp.io/servers/report-pure-news/pure/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/report-pure-news/pure/changelog.json
- HTML version of this page: https://verifymcp.io/servers/report-pure-news/pure