pumpdata

fun.pumpdata由 pumpdata.fun 發布官方發布者v0.3.2更新於 Oct 27, 2026

Check a pump.fun coin, dev or wallet: deployer record, bundle, PnL. Every pump.fun trade, ever.

已驗證Streamable HTTP可網頁執行金融資料與分析

概覽

AI 產生的概覽

針對 pump.fun 的遠端 MCP 伺服器:查詢代幣、部署者與錢包,取得基準機率,並用完整交易歷史回測選幣。

可以做什麼
  • 依代號或名稱尋找代幣,並查看某個 mint 的發行紀錄:部署者歷史、建立時的綑綁買入、內部人占比,以及相似發行的後續表現
  • 依地址查核錢包,歸類為贏家、機器人、拋售者或新錢包,並附上背後的 SOL 數據
  • 依錢包地址查看部署者戰績,包括近 90 天各次發行的結果
  • 取得某個市值區間的基準機率:3 小時內達到 2 倍、5 倍、10 倍、20 倍的比例
  • 找出與某代幣同年齡段最相似的發行,以及它們接下來 24 小時的表現
  • 用時間戳與部位回測最多 500 筆選幣,並輪詢任務取得逐筆與彙總結果
適用情境
適合需要研究 pump.fun 代幣、部署者或錢包,或想用歷史基準機率與回測檢驗交易想法、而非憑感覺判斷的情境。也適合已能處理付費 API 呼叫的加密研究與代理工作流程。
執行需求
遠端 streamable HTTP 端點 pumpdata.fun,不需帳號或 API 金鑰。付費呼叫透過 x402 以 Solana 主網 USDC 結算:用戶端簽署 USDC 轉帳,並帶 PAYMENT-SIGNATURE 標頭重試,通常搭配 x402 用戶端函式庫與 PUMPDATA_PAYER_KEY 之類的付款金鑰。錢包需有 USDC,但不需要 SOL。部分端點與每日基準機率檔案免費。
安裝前請注意
多數查詢按次收費(例如 0.005 至 0.01 美元,回測 2 美元),助理可能在未詢問的情況下花費 USDC。付費呼叫需要用錢包金鑰簽署 USDC 轉帳,務必避免把金鑰寫進程式碼或提交到版本庫。回測任務為排隊執行,需要輪詢結果。資料僅涵蓋 pump.fun,且此服務與 pump.fun 無隸屬關係。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 pumpdata,將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Web executable,透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。

交給代理程式安裝

把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式,或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南,先向你展示發布者、端點和登入方式,經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。

閱讀 https://sourceweft.com/mcp/fun.pumpdata%2Fpumpdata/install.md,並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前,先告訴我它的發布者、端點和登入方式,等我確認。不要把 API 金鑰寫進命令或我會提交的檔案;問我金鑰應從哪裡取得。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。

{
  "mcpServers": {
    "pumpdata": {
      "type": "http",
      "url": "https://pumpdata.fun/mcp"
    }
  }
}

README

pumpdata examples

Calling pumpdata.fun from an agent or a script: every pump.fun trade, ever, bonding curve and PumpSwap, since pump.fun's first day, read from the chain's ledger with the dead coins kept, sold by the call in USDC over x402 on Solana. No key, no account.

callasksprice
GET /baserate?band=15k-28k&from=<iso>&to=<iso>&venue=anyhow many coins first traded inside a market-cap band in a window, and how many reached 2x, 5x, 10x, 20x within 3 h$0.005
POST /wallets {"addresses": [...], "mint": "<optional>"}what up to 50 wallets have been: winner, bot, supply seller, new, with the SOL behind it$0.01
GET /launch/{mint}the deployer's record, the bundle at creation, the insiders' share, and how launches that looked the same went over 24 h$0.005
POST /replay {"picks": [{"mint", "at", "size_sol"}, ...]}up to 500 picks replayed against the chain's history with fees and fills (a queued job; poll GET /replay/{id})$2

Free, no payment: yesterday's base rate for every band at /public/baserate.json, refreshed hourly.

Contract: /openapi.json. Docs for agents: /llms.txt. A skill: /skill.md.

How a call is paid

  1. Call without payment. The answer is 402 with the offer in the body and in the PAYMENT-REQUIRED header: price, payee, network (USDC on Solana mainnet), and a Bazaar declaration of the inputs.
  2. Sign a USDC transfer for that amount with your wallet (the facilitator pays the network fee; you need no SOL).
  3. Call again with the signed payment in PAYMENT-SIGNATURE. The answer is the data, with the receipt in PAYMENT-RESPONSE.

The x402 client libraries do steps 2 and 3 for you. Every answer carries X-Data-As-Of (the build it comes from) and X-Data-From (where the data begins). A window with no data answers 404 and costs nothing.

The examples

  • curl.sh: the 402 and the free file, no wallet needed.
  • node.mjs: a paid call with @x402/fetch and a Solana keypair.
  • python.py: the 402 and the free file from Python; the paid retry with the x402 package.
  • mcp.md: the same calls as MCP tools (Claude Code, Cursor, Cline, Claude Desktop).

Check the base rate before you ape: agent recipes

A paid GET /baserate ($0.005) in four shapes, each 17-21 lines. The payer key comes from PUMPDATA_PAYER_KEY (base58, or the solana-keygen JSON array). The wallet needs USDC and no SOL. Never commit the key.

filewhatrun
x402-fetch.tsplain fetch with the official client, @x402/fetch + @x402/svmnpm run fetch
elizaos-action.tsElizaOS (@elizaos/core 1.x): a pumpdata plugin with a PUMPDATA_BASE_RATE actionnpm run eliza
solana-agent-kit-tool.tssolana-agent-kit v2: an Action in a plugin, run through executeActionnpm run agent-kit
vercel-ai-tool.tsVercel AI SDK (ai v7): a tool() for generateText / streamTextnpm run ai-sdk
npm installexport PUMPDATA_PAYER_KEY='<secret key>'npm run fetch        # yesterday's (UTC) $15-28K base rate, any venuenpm run typecheck

The three framework files reuse baseRate() from x402-fetch.ts. Run on their own, they call the action or tool directly, the way the framework would, so no model or agent is needed to try them.

Not affiliated with pump.fun.

來源:README.md,提交 204616c

工具

9

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).

輸入參數day

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.

輸入參數q必填limit

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.

輸入參數to必填band必填from必填venuepayment

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) and the numbers behind it: pnl_sol, put_in, took_out, coins, first_seen. 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.

輸入參數mintpaymentaddresses必填

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, curve progress, 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 deployed this token, is this dev legit. Facts, no verdict. $0.005 a call, USDC on Solana over x402, or a free key.

輸入參數mint必填payment

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.

輸入參數address必填payment

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.

輸入參數mint必填limitpayment

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.

輸入參數exitpicks必填paymentlatency_sbankroll_sol

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.

輸入參數id必填

版本歷史

3
  1. v0.3.2最新Oct 21, 2026
  2. v0.3.1Oct 17, 2026
  3. v0.3.0Oct 17, 2026

評分

已滿足適用檢查項的 100%

該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通必需25 分
  • 已宣告認證方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分