GroundedKit Marketing Stats Checker
Measured conclusion: Deep-tested. L2 outcome: tools_ok.
Check marketing and influencer stats against primary sources: verdict, source, safe wording.
| Author | com.groundedkit |
|---|---|
| Access | remote |
| Publisher key required | No |
| Measured state | Deep-tested |
| L1 liveness | alive |
| L1 latency | 2934 ms |
| Last measured | 2026-10-26 |
Add to your agent
Copy this into your MCP client config:
{
"mcpServers": {
"GroundedKit Marketing Stats Checker": {
"url": "https://groundedkit.com/mcp",
"transport": "streamable-http"
}
}
}
Measured tools (5)
check_statread-onlyPaste 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.
Parameters:
text(required) — string — The statistic as you saw it, e.g. 'influencer marketing returns $5.78 per $1'
Hints: read-only yes · destructive no · idempotent yes · open-world no
verify_textread-onlyPaste 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.
Parameters:
text(required) — string — The draft to check, up to 20,000 characters. Longer input is cut at 20,000 characters and flagged as truncated.max_statements— integer — Maximum statements to check, 1 to 60 (default 40)
Hints: read-only yes · destructive no · idempotent yes · open-world no
search_claimsread-onlyKeyword 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.
Parameters:
query(required) — string — Words or numbers to search for, e.g. 'email ROI' or 'trust influencers'. Empty string lists everything.limit— integer — Maximum results, 1 to 50 (default 10)verdict— string — Optional verdict filter
Hints: read-only yes · destructive no · idempotent yes · open-world no
get_claimread-onlyFull 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.
Parameters:
id(required) — string — Claim id/slug, e.g. 'email-marketing-roi-36-to-1', or its groundedkit.com URL
Hints: read-only yes · destructive no · idempotent yes · open-world no
list_verdictsread-onlyThe four verdicts (verified, misquoted, outdated, unsourced) with definitions and how many claims carry each, plus confidence levels and dataset info.
Hints: read-only yes · destructive no · idempotent yes · open-world no
Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.