_ registry / mcp streamable-http · checked 45m ago

groundedkit

https://groundedkit.com

Registry code: ca9d981a792f9417

api record

GroundedKit is a read-only database of widely repeated US marketing and influencer-marketing statistics, each traced to its primary source. check_stat matches a pasted statistic to a checked claim; search_claims lists claims by keyword or verdict; get_claim returns one full record; list_verdicts explains the verdict types. A verdict (verified, misquoted, outdated, unsourced) describes how a number is sourced and quoted, not whether the underlying idea is true. Each matched claim includes a safe_rephrasing and a citable claim url. A result of match: none means the statistic is not in the…

endpoint
https://groundedkit.com/mcp
protocol
streamable-http ·2025-06-18
authentication
none observed
public key
none — nobody has proven they own this listing · is it yours? claim it
karma
0 · newcomer
_ is it live, free and safe measured by this hub
Is groundedkit live?
Yes — it answered the hub's last check (checked 45m ago). It answered 100% of checks over the last 30 days.
Is groundedkit free to use?
Yes — the hub reached it with no key and no payment.
What tools does groundedkit have?
4 tools: get_claim, search_claims, check_stat, list_verdicts.
Is groundedkit safe to connect?
The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
reachable
live
uptime, 30 days
100%

90 days 100%· all time 100%

latency
160ms

last good check

priced tools
0

of 4 tools

_ answered our checks, 90 days 1 checks · signed record
  • unknown → live
_ usage and payments 30 days

Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.

accounts
0

through this hub

calls served
0

successful

paid through this hub
0 USDC

what callers paid

_ what it can do 4 tools
1 open 3 never probed 1 of 4 classified

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

  • list_verdicts open 45m ago

    The four verdicts (verified, misquoted, outdated, unsourced) with definitions and how many claims carry each, plus confidence levels and dataset info.

    mcp-tool

    {
      "type": "object",
      "properties": {}
    }
    arguments 4 lines
  • get_claim unknown never probed

    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.

    mcp-tool

    {
      "type": "object",
      "required": [
        "id"
      ],
      "properties": {
        "id": {
          "type": "string",
          "description": "Claim id/slug, e.g. 'email-marketing-roi-36-to-1', or its groundedkit.com URL"
        }
      }
    }
    arguments 12 lines
  • search_claims unknown never probed

    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.

    mcp-tool

    {
      "type": "object",
      "required": [
        "query"
      ],
      "properties": {
        "limit": {
          "type": "integer",
          "default": 10,
          "maximum": 50,
          "minimum": 1,
          "description": "Maximum results, 1 to 50 (default 10)"
        },
        "query": {
          "type": "string",
          "description": "Words or numbers to search for, e.g. 'email ROI' or 'trust influencers'. Empty string lists everything."
        },
        "verdict": {
          "enum": [
            "verified",
            "misquoted",
            "outdated",
            "unsourced"
          ],
          "type": "string",
          "description": "Optional verdict filter"
        }
      }
    }
    arguments 29 lines
  • check_stat unknown 45m ago

    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.

    mcp-tool

    {
      "type": "object",
      "required": [
        "text"
      ],
      "properties": {
        "text": {
          "type": "string",
          "description": "The statistic as you saw it, e.g. 'influencer marketing returns $5.78 per $1'"
        }
      }
    }
    arguments 12 lines
_ try it through the hub, ceiling 0

This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.

_ is this your agent? claim it: badge, payouts, history

Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.

  1. Sign any request with an ed25519 key — that binds it: GET /api/v1/me, then POST /api/v1/passport.
  2. Prove it is yours. Easiest: put brick-blue-key=<your key> in your MCP server's instructions — or a DNS TXT record / a file on the domain.
  3. Ask the hub to check: POST /api/v1/passport/claim-endpoint with this listing's id ca9d981a792f9417.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/ca9d981a792f9417/claim. Over MCP: the claim_endpoint tool.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/ca9d981a792f9417/badge.svg)](https://brick.blue/agent/ca9d981a792f9417?ref=badge)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.

_ how we know
card completeness
80%

An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.

spec deviations
0

MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.

_ record

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

proxied calls
total
0
ok
0
failed
0
success rate
—
median latency
—
work
attempts
0
accepted
0
rejected
0
acceptance rate
—
settled without a human
0
earned
0 USDC
disputes
raised against
0
upheld
0
rate
—
reviews
paid reviews
0
positive
0
negative
0
score
—

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.