Every change Wellknown observed on this MCP server, newest first, with what it was before and what it became. Tool-surface changes carry the definition diff. Nothing here is edited after the fact.
Changed the definition of "groundtruth_kol_board" and "groundtruth_kol_feed"
undefinedWhat the KOL wallet launched, and how it ended. Rugged of resolved, seconds to the pull, every count with its N. One call. The wallets on kolscan, the pump.fun leaderboard, ⟨64 unchanged words⟩
undefinedWhat the KOL wallet launched, and how it ended. Rugged of resolved, seconds to the pull, every count with its N. One call. JUST IN: launches by wallets on the ⟨43 unchanged words⟩
Changed the definition of "groundtruth_creator_flag" and "groundtruth_kol_board"
⟨31 unchanged words⟩ KOL list (kolscan, the pump.fun leaderboard, kolscan.fun, KolHood, Kolosseum) -- tag KOL or TOP PROFIT, the ⟨198 unchanged words⟩
undefined The wallets on kolscan, the pump.fun leaderboard, kolscan.fun, KolHood andkolscan.funKolosseum that launched coins, counted by GROUNDTRUTH: tag ⟨53 unchanged words⟩
Added "groundtruth_kol_board" and "groundtruth_kol_feed"; changed the definition of "groundtruth_creator_flag" and "groundtruth_scan_coin" (13 tools before, 15 now)
What the KOL wallet launched, and how it ended. Rugged of resolved, seconds to the pull, every count with its N. One call. kol: when the creator is on a public KOL list (kolscan, the pump.fun leaderboard, kolscan.fun) -- tag KOL or TOP PROFIT, the lists, tg / x / verified as yes-no, the list rank, listed now; null when it is on none. Never a name or handle. One creator in, one small answer out: ⟨167 unchanged words⟩
What the KOL wallet launched, and how it ended. Rugged of resolved, seconds to the pull, every count with its N. One call. When the dev is on a KOL list, envelope.kol carries tag KOL / TOP PROFIT, the lists, yes-no flags and rank (never a name). Look up one token and return what GROUNDTRUTH Changed the definition of "groundtruth_creator_flag", "groundtruth_scan_coin", "groundtruth_screen_creator" and 1 more
⟨96 unchanged words⟩ for a creator not in our count. Thedata behind itcountsisare a batchexportrecount; LIVE FIELDS,sofromathecreatormintwhofeedlaunchedeveryin5
Added "groundtruth_copycheck" and "groundtruth_wallet_record"; changed the definition of "groundtruth_creator_flag", "groundtruth_creator_replay", "groundtruth_scan_coin" and 3 more (11 tools before, 13 now)
⟨50 unchanged words⟩ and rugged_resolved / faded_resolved as x/y, allascountedofto therecord'sbuild time of the data and from launch outcomes only. The cheapest call ⟨19 unchanged words⟩ is null, never false, for a creatorwe havenotnoinrecordourof.count. The data behind it is a batch export
Changed the definition of "groundtruth_creator_flag", "groundtruth_seal_call" and "groundtruth_time_to_rug"
⟨18 unchanged words⟩ baseline and the multiple that justifies the verdict. Also returns TTR -- ttr_median, ttr_p25 and ttr_mean, in seconds from launch to rug over this creator's rugged launches, with ttr_n and n_rugged -- and rugged_resolved / faded_resolved as x/y, all as of the record's build time and from launch outcomes only. The cheapest call on this server -- use ⟨56 unchanged words⟩
{"properties":{"band":{"description":"theyourbandown
Changed the definition of "groundtruth_screen_creator"
⟨13 unchanged words⟩ launches: the role each played (creator,operator_pool,repeat_buyer, one_off), how many of this creator's ⟨7 unchanged words⟩ many it was early in anywhere, andthat wallettheoperator'screator's own rugrate. Also returns the apparent-versus-true collapse: how many wallets LOOK independent versus how many distinct actors they actually are, after merging wallets with near-identical launch histories. Rates comeratewithagainst the chain baseline, because a rate without its baseline is not a finding.ThisItisdoes
Unknown → Live
Certificate recorded, valid to 2026-12-01
Authorization not required
First tool surface recorded: 11 tools (server version 1.0.0)
https://api.groundtruths.xyz/mcp (mcp_streamable_http) — from mcp_registry, with the record
Showing the latest 12 events. The API returns up to 500 and filters by kind: ?kind=tool_surface_changed
undefined The wallets on kolscan, the pump.fun leaderboard and kolscan.fun that launched coins, counted by GROUNDTRUTH: tag KOL or TOP PROFIT, launches, rugged / resolved, PULL, bonded, last mint, and list juice (Telegram / X / verified as yes-no, list rank, listed now). Wallets only, never a name. Free: the top 3 per list and every list total; with an API key, every row (or /v1/kol over x402).
undefined JUST IN: launches by wallets on the KOL and top-profit lists, newest first, each with that wallet's rugged / resolved before it; AGAIN: rugs on their coins with the seconds to the pull. 10 minutes behind. Free: the newest 3; with an API key, 30 (or /v1/kol/feed over x402).
⟨55 unchanged words⟩ site performs when someone pastes a contract address. The answer carries the envelope; its live block holds the dev's last_mint_live, launched_live, bonded_live, mints_since_asof and ticker_asof (the newest mint the feed has seen). A dev WALLET pasted here answers not_token plus that dev's creator_record and the same live fields.
⟨59 unchanged words⟩ It does not say who owns the wallets. LIVE FIELDS, from the mint feed every 5 s: last_mint_live (unix s of the dev's newest mint), launched_live, bonded_live and mints_since_asof; ticker_asof = the newest mint the feed has seen. A row with no mints_since_asof is not live: refuse it. bonded_asof dates the recount part; peak / pull and ttr_* are history (peak_proven / pull_proven false), not a trade signal; known_bad is the census rule.
⟨259 unchanged words⟩ buys in the tape range). Counts only. creator_record (a deployer) carries the LIVE FIELDS, from the mint feed every 5 s: last_mint_live (unix s of the dev's newest mint), launched_live, bonded_live and mints_since_asof; ticker_asof = the newest mint the feed has seen. A row with no mints_since_asof is not live: refuse it. bonded_asof dates the recount part; peak / pull and ttr_* are history (peak_proven / pull_proven false), not a trade signal; known_bad is the census rule.
⟨60 unchanged words⟩ before the band p25, because the publishedrecorddata carries the peak and the final multiple, ⟨41 unchanged words⟩ total. Solana only today: the Robinhood outcomerecorddata carries no peak multiple, so neither row can be computed there.
Look up one token and return what GROUNDTRUTHrecordedcounted about it: the outcome label (rugged, died, graduated, survived, or no outcomerecorded), liquidity and market-cap figures, holder counts, and therecordlaunch counts of the wallet that launched it. Accepts a ⟨24 unchanged words⟩
How often callssealedstamped under this API key were right. Groups them ⟨6 unchanged words⟩ coin actually did, resolved from the samerecorddata the card reads. A call whose coin has ⟨39 unchanged words⟩
⟨83 unchanged words⟩ is null, NEVER false, for a creatorwe havenotnoinrecordourofcount:absencenotisinnotourinnocence.count means nothing either way.
SealStamp a verdictBEFOREahead of the outcomeexists, so it can bescoredcounted later. This is the honesty mechanism: the ⟨15 unchanged words⟩ be edited or removed after the coin resolves.SealStamp every call you make, including the ones ⟨23 unchanged words⟩
For a copy bot about to follow a wallet into a coin: the coin's creator counts (to that coin's launch when we have them), the wallet's counts from the capture tape, and one line built from those counts only, e.g. "creator: SAME HAND 12/12 RUGGED (counted to this coin's launch) · wallet: 393/1,241 sells within 60 s before a rug, below the all-wallet rate · 701/2,450 buys where a wallet that first bought 1-2 s later still held at the rug, below the all-wallet rate · ... · tape 2026-08-29..2026-09-28". Solana only. Counts only.
One WALLET in, its counts out, from GROUNDTRUTH's own Solana capture tape (not a third party feed). Each of four fields is x/n with a one-line definition of n beside it, its rate, the same rate over all wallets, and the word above, below or about ("about" = within 2 percentage points): bad_share (buys in coins from creators with 5+ launches, 80%+ rugged, judged at each coin's launch; n = buys in coins whose dev we have counted), pre_rug_exits (n = the wallet's sells in coins that rugged; x = those in the 60 s up to the rug), copier_bagholder (buys where a wallet that first bought 1-2 s later …
HowWITHDRAWN 2026-09-29: the bands did not beat an age-matched baseline, so this now returns nulls plus band_withdrawn. Was: how fast coins in a given risk band actually ⟨91 unchanged words⟩
{"properties":{"band":{"description":"the bandwithdrawn: GROUNDTRUTHassigned atnothelongertimeassignsofatheband;callignored","enum":["RED","AMBER"," ⟨32 unchanged words⟩
⟨52 unchanged words⟩ "description":"Optional filter. Omit for all roles.operator_pool is the row that matters most.","enum":["","operator_pool","repeat_buyer","one_off"],"type":" ⟨5 unchanged words⟩