# GroundedKit Marketing Stats Checker

> Check marketing and influencer stats against primary sources: verdict, source, safe wording.

- name: com.groundedkit/marketing-stats
- version: 1.0.0
- connection class: R0 (autonomous)
- trust: 82/100 flags: no-repository
- quality: 89/100 (new)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/com.groundedkit%2Fmarketing-stats
- tools: https://api.protogrid.dev/v1/servers/com.groundedkit%2Fmarketing-stats/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "marketing-stats": {
      "type": "http",
      "url": "https://groundedkit.com/mcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 98
- freshness: 100
- provenance: 55
- drivers: +dns-namespace +website +reachable +uptime-94% +updated-4d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 89/100 (new)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 100 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 5 of 5 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- pass `tools.token_cost`: about 851 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: n/a (weight 15)

- n/a `stability.changes`, `stability.rug_pull`: tool history recorded for 4 of the 7 days needed

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 5, about 851 tokens to load them all
- tool set hash: ece1078ad2c8753b601e5499aacbe81f
- tools last changed: 2026-10-17T03:42:12.585Z
- badge: [![protogrid quality](https://protogrid.dev/badge/com.groundedkit/marketing-stats.svg)](https://protogrid.dev/servers/com.groundedkit/marketing-stats)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-17 `verify_text` added
  - Paste a whole draft (up to 20,000 characters: a blog post, deck notes, an email, a social caption). Splits it into sentences, keeps each sentence that contains a number or statistic, and matches each one against the checked claims. Returns one row per statement with the numbers found, the match level, verdict, safe rephrasing and claim URL, or status not_in_database, plus counts by status and verdict. Unmatched statistic text is logged anonymously (date and text only) to guide which stats get checked next.
- 2026-10-17 `check_stat` changed (description)
  - before: Paste a marketing or influencer-marketing statistic (a sentence or a whole paragraph), or ask for a reference number (e.g. 'what share of US adults use TikTok'). Returns the best-matching checked claim with its verdict, confidence, primary source, what the source actually says, a safe rephrasing and the claim URL, plus its kind (stat_check or reference_fact), as_of date and last_checked date, and close alternatives. Returns match: none when the stat is not in the database.
  - after: Paste a marketing or influencer-marketing statistic (a sentence or a whole paragraph), or ask for a reference number (e.g. 'what share of US adults use TikTok'). Returns the best-matching checked claim with its verdict, confidence, primary source, what the source actually says, a safe rephrasing and the claim URL, plus its kind (stat_check or reference_fact), as_of date, last_checked date and stale flag (last checked more than 180 days ago), and close alternatives. Returns match: none when the stat is not in the database.

Full history: https://api.protogrid.dev/v1/servers/com.groundedkit%2Fmarketing-stats/changes

## Remotes

- https://groundedkit.com/mcp (streamable-http, auth none, reachable true, uptime30d 0.9375)

## Packages

_none_

## Tools (5)

- `check_stat`: Paste a marketing or influencer-marketing statistic (a sentence or a whole paragraph), or ask for a reference number (e.g. 'what share of US adults use TikTok'). Returns the best-matching checked claim with its verdict, confidence, primary source, what the source actually says, a safe rephrasing and the claim URL, plus its kind (stat_check or reference_fact), as_of date, last_checked date and stale flag (last checked more than 180 days ago), and close alternatives. Returns match: none when the stat is not in the database.
- `get_claim`: Full record for one checked claim by id (slug) or claim page URL: verdict, confidence, origin, exact quote, method and sample, drift, publisher interest, safe rephrasing and every source we opened.
- `list_verdicts`: The four verdicts (verified, misquoted, outdated, unsourced) with definitions and how many claims carry each, plus confidence levels and dataset info.
- `search_claims`: Keyword search over all checked marketing statistics (claim text, common phrasing, origin publisher). Optionally filter by verdict. Returns short summaries; get_claim returns the full record for an id.
- `verify_text`: Paste a whole draft (up to 20,000 characters: a blog post, deck notes, an email, a social caption). Splits it into sentences, keeps each sentence that contains a number or statistic, and matches each one against the checked claims. Returns one row per statement with the numbers found, the match level, verdict, safe rephrasing and claim URL, or status not_in_database, plus counts by status and verdict. Unmatched statistic text is logged anonymously (date and text only) to guide which stats get checked next.