pumpdata

Measured conclusion: Alive, not deep-tested. L2 outcome: not_attempted.

pump.fun history for trading agents: base rates, wallet and launch records, replay. Paid per call.

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "pumpdata": {
      "url": "https://pumpdata.fun/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (11)

• stats

  Pump.fun stats for one UTC day, free: coins launched and graduated, the graduation rate, SOL and USD volume, traders; the top coins by peak market cap and by volume; the deployers whose coins did best, with their record; the instant and fastest graduations; launches and the 1 h graduation rate per UTC hour; launches dead by their second hour. For: pump.fun today or yesterday, how many coins launched, how many graduated, the biggest coin of the day. `checks` lists any number that failed a sanity check: never quote one. `summary` is one paragraph to quote. Each coin and deployer names the paid call that goes deeper (launch_record, deployer_record).

  Parameters:

  • day — string — a UTC day, YYYY-MM-DD; default the latest

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• find_coin

  Free. The pump.fun coins a ticker or name means, newest first, so a coin named in a chat can be looked up by its mint: for each, the mint (the contract address, CA), its name and ticker, when it was created, its deployer with their launches and graduations, whether it graduated, its market cap at five minutes and its first-day peak. For: what is $KIMCHI's CA, which Kimchi is the real one, find this coin by name, the mint for this ticker. Covers every coin that completed its bonding curve (about 300K); a coin still on its curve is not here yet. A mint given as q returns that coin's name. Then launch_record on the mint.

  Parameters:

  • q (required) — string — a ticker ($KIMCHI or KIMCHI), a name, or a mint
  • limit — integer — coins to return, newest first; default 20

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• check_coin

  Free. The pre-buy check of one pump.fun coin by its mint (contract address, CA), in one call: the findings as sentences (answer), short flags with a sentence each (serial_launcher, never_ran, curve_bought_at_launch, bundled, insiders, lookalikes_die), rules_say (skip, or no flags: your call) and the launch record behind them: the deployer's record, the bundle at creation, the insiders' share, who holds most, how launches like it went. For: check this coin, is this a rug, should I buy this, is this coin bundled. Facts, no verdict.

  Parameters:

  • mint (required) — string — the coin's mint address (base58)

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• top_wallets

  Free. The pump.fun wallet leaderboard: wallets that win over their whole record (took out 10+ SOL and 1% more than they put in over 20+ coin-weeks) and traded in the last ~20 days, best first, each with why, its SOL in and out, its coins and its recent pace (trades a day, median hold). followable: true keeps the ones a copier can keep up with (under 20 trades a day, a median hold of 2 minutes or more, under half its trades fast). For: who should I copy trade, the best pump.fun traders, smart money wallets. Not pump.fun's own leaderboard, which ranks recent profit. Then wallet_records for any wallet's full record.

  Parameters:

  • limit — integer — wallets to return, best first; default 25
  • followable — boolean — only wallets a copier can keep up with; default false

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• base_rate

  The odds for pump.fun coins in a market-cap band: how many first traded inside the band in a window, how many of those then reached 2x, 5x, 10x and 20x within 3 h, and the median peak. For: the base rate, what are the odds a $20K coin does 10x, how often does it happen anyway. A crossing is a coin's first trade with a market cap inside the band (a coin that jumps over the band in one trade has none); the peak is the highest market cap, curve or pool, in the 3 h after it; USD is at the SOL price of the trade's hour. $0.005 a call, USDC on Solana over x402, or a free key.

  Parameters:

  • band (required) — string — market-cap band in USD, e.g. 15k-28k; each edge snaps to the nearest of 5k, 10k, 15k, 20k, 28k, 40k, 60k, 100k, 250k, 1000k, and the answer says the band used
  • from (required) — string — window start, ISO 8601 UTC
  • to (required) — string — window end; a crossing needs its 3 h after, so an end under 3 h before the data's as-of is cut
  • venue — string — default any
  • payment — string — the x402 PAYMENT-SIGNATURE value for this exact call (USDC on Solana). Leave it out to get the offer: the price, the payee and the network come back as the error content and as _meta['payment-required'].

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• wallet_records

  Check pump.fun wallets by address: what each has been since day one, its class by rule (winner: took out 10+ SOL and 1% more than it put in over 20+ coin-weeks; net_loser: put in 50+ SOL more than it took out; bot: a sniper (20+ coins bought in their create block, half or more of its new coins) or 1,500+ trades a day; supply_seller: took out 1.5x what it put in, 100 SOL or more; new: no record before the mint you name, or before today; none: no rule fits, usually too young for them), why (the rule it met, with its numbers) and the numbers behind it: pnl_sol, put_in, took_out, coins, first_seen, recent (its pace). For: who is buying this coin, is this wallet a bot, a wallet's PnL, a holder check on the top buyers. Up to 50 addresses a call. $0.01 a call, USDC on Solana over x402, or a free key.

  Parameters:

  • addresses (required) — array — base58 wallet addresses
  • mint — string — optional: the coin they are buying; a wallet with no record before its creation is 'new'
  • payment — string — the x402 PAYMENT-SIGNATURE value for this exact call (USDC on Solana). Leave it out to get the offer: the price, the payee and the network come back as the error content and as _meta['payment-required'].

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• launch_record

  Check a pump.fun coin by its mint (the contract address, CA): who launched it and the deployer's record at the launch (launches before it, graduations, the gap to the previous one, launches in the last day), the bundle at creation (buyers in the first 10 s and the share of supply they took), the insiders' share now, whether one or two wallets bought the whole curve as it launched (curve_bought_at_launch, with the share they still hold), curve progress, the market cap now and the real SOL behind it (sol_reserve_now), its holder count, its 20 biggest wallets now (top_holders), the 20 that made the most SOL on it with their classes (top_traders, coins launched since the tables' build), and how launches that looked the same at this age went over their next 24 h (graduation share, peak and close quantiles, how many died). For: check this coin, a rug check, is this coin bundled, who holds it, who made money on it, who deployed this token, is this dev legit. Facts, no verdict. $0.005 a call, USDC on Solana over x402, or a free key.

  Parameters:

  • mint (required) — string — the coin's mint address (base58)
  • payment — string — the x402 PAYMENT-SIGNATURE value for this exact call (USDC on Solana). Leave it out to get the offer: the price, the payee and the network come back as the error content and as _meta['payment-required'].

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• deployer_record

  A pump.fun dev's record by wallet address, no coin needed: launches, graduations, best run, the gap between launches; over the last 90 days how many of its launches doubled, did 10x, held at 2x a day later or died; its newest launches; and the base rate for its next launch from deployers with the same record. For: this dev's history, a serial deployer, has this creator rugged before, the deployer's track record. Facts, no score. $0.005 a call, USDC on Solana over x402, or a free key.

  Parameters:

  • address (required) — string — the deployer's wallet address (base58)
  • payment — string — the x402 PAYMENT-SIGNATURE value for this exact call (USDC on Solana). Leave it out to get the offer: the price, the payee and the network come back as the error content and as _meta['payment-required'].

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• similar_launches

  The pump.fun launches most like this coin at the same age, named by mint, and how each went over its next 24 h (peak, close, dead or graduated): the same deployer's prior launches first, then the nearest of the last 90 days by the deployer's record, the first-10 s buyers, the insiders' share and curve progress, each saying why it is similar. For: coins like this one, what happened to launches like this, comparables. Not a prediction: what launches that looked like this did next. $0.005 a call, USDC on Solana over x402, or a free key.

  Parameters:

  • mint (required) — string — the coin's mint address (base58)
  • limit — integer — comparables to return, default 10
  • payment — string — the x402 PAYMENT-SIGNATURE value for this exact call (USDC on Solana). Leave it out to get the offer: the price, the payee and the network come back as the error content and as _meta['payment-required'].

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• replay

  Backtest pump.fun picks: picks with timestamps and sizes in; what they made, pick by pick and in sum, every pick counted, the dead ones included, filled at the PumpSwap pool as it stood after your latency (graduates only; bonding-curve picks, and picks outside the archive, are counted in skipped_not_covered until curve fills ship), with every fee, the fixed costs and the bankroll you set. For: backtest my calls, would this strategy have made money, replay these picks with real fills. The most recent eight weeks come back apart from the rest, once per rule to each payer. A run is a queued job: the result is {id, state: queued}; poll replay_result with the id. $2 a run, USDC on Solana over x402; a run that fails is rerun free on the same id.

  Parameters:

  • picks (required) — array — up to 500 a run for now; split the rest into another run
  • exit — object — take (x the entry), trail (share off the high), hold_s (seconds); any combination
  • payment — string — the x402 PAYMENT-SIGNATURE value for this exact call (USDC on Solana). Leave it out to get the offer: the price, the payee and the network come back as the error content and as _meta['payment-required'].
  • latency_s — number — seconds from the decision to the fill
  • bankroll_sol — number — SOL at risk at once; a pick with no room is skipped

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• replay_result

  A replay's result: the job's state, and the replay once done with the execution model it charged. Free; the id is the receipt.

  Parameters:

  • id (required) — string — the id from replay

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

Publisher website Repository

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.