GroundedKit MCP server

• Registry namecom.groundedkit/marketing-statsverified in the MCP registry

The registry name sits under groundedkit.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

• Stateanswerschecked 2026-10-27
• Tools5
• Server calls itselfgroundedkit
• Server version1.0.0
• Protocol version2025-06-18

On 2026-10-27 the server answered initialize and tools/list without a sign-in. First answer in 79 ms.

• Its tools do every use case we checked: trace a marketing stat back to its original source; have AI agents verify statistics before they cite them.
• Checked on 1 of the 7 days it takes to judge reliability.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

• INITE MCP scoreafter a weeka score needs 7 daily checks: 1 so far
• What an agent can do with it2 of 2 use cases
• Answeredmeasuring1 of the 7 daily checks it takes to print a share
• Median first answer277 ms
• Space in an agent's context≈ 757 tokensthe definitions of all its tools (5), which an agent carries on every turn
• Tool definitionsA · 100 of 100
• Typed results0 of 5 toolsdeclared outputSchema: results come typed, read once

• Every tool passes all six checks.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

• 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…

• 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…

• 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.

• 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.