PumpPill — token safety and measured outcomes

Token safety, FOMO trader flow and graded calls on Robinhood Chain and Solana; x402 pay-per-call

我該用這個嗎

品質與安全性

A
說明品質
100%
結構描述完整度
68%
命名品質
82%
汙染風險
100%
權限相符程度
100%
協定合規性
100%

根據工具定義與協定合規性的自動化分析。

上下文成本

~3,222Token(工具定義)
~379 B典型回應大小
顯著的注意力影響(128k 上下文的 2.52%)

這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高,可用於其他工作的注意力就越少。

安裝

一鍵安裝

將以下內容加入你的 `claude_desktop_config.json` 檔案:

{
  "mcpServers": {
    "token-safety": {
      "url": "https://api.pumppill.org/mcp"
    }
  }
}

遠端端點

https://api.pumppill.org/mcpstreamable-http

它能做什麼

工具清單

工具(20)

🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
🟢rh_token_safety(address)

Stored safety read for one Robinhood Chain token (0x + 40 hex): sellability, launch flags with evidence, where the launch money went, and the move since PumpPill first logged it. Never triggers a scan. found=false means not yet indexed, not safe; the miss is queued for reading. deep=true means the economics, lock, operator and thesis passes ran. A flag is a finding, not a prediction.

輸入結構描述

{
  "type": "object",
  "properties": {
    "address": {
      "title": "Address",
      "type": "string"
    }
  },
  "required": [
    "address"
  ],
  "title": "rh_token_safetyArguments"
}
🟢rh_ticker_resolve(symbol)

The ONE Robinhood Chain contract worth naming for a ticker: alive, $10K+ in its pool, not flagged HIGH or CRITICAL. Other contracts using the name come back as a count, never a list. found=false means nothing clears the gate, which is itself the answer.

輸入結構描述

{
  "type": "object",
  "properties": {
    "symbol": {
      "title": "Symbol",
      "type": "string"
    }
  },
  "required": [
    "symbol"
  ],
  "title": "rh_ticker_resolveArguments"
}
🟢rh_deployer_record(address)

What one Robinhood Chain wallet has launched and how those went: tokens, liveness, liquidity, which crossed $100K. Factory and relayer wallets above the launch ceiling get no record, and so does a wallet with a single launch. No success rate is computed: the rows hold only what crossed.

輸入結構描述

{
  "type": "object",
  "properties": {
    "address": {
      "title": "Address",
      "type": "string"
    }
  },
  "required": [
    "address"
  ],
  "title": "rh_deployer_recordArguments"
}
🟢rh_flagged_recent(limit)

Tokens whose latest scan in the last 30 days found HIGH or CRITICAL structural risk, with the findings named. Each is a finding with evidence, not a verdict on price and not an accusation. Shows what the current wave of bad launches looks like; never a list to trade against.

輸入結構描述

{
  "type": "object",
  "properties": {
    "limit": {
      "default": 25,
      "title": "Limit",
      "type": "integer"
    }
  },
  "title": "rh_flagged_recentArguments"
}
🟢rh_stock_pairs(stock)

Memecoins quoted in TOKENIZED STOCKS on Robinhood Chain. Pass a stock symbol (NVDA, SPY, TSLA) for the trading, unflagged tokens quoted in it with liquidity and latest scan risk; omit it for every stock with a count. This pairing exists on no other chain.

輸入結構描述

{
  "type": "object",
  "properties": {
    "stock": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Stock"
    }
  },
  "title": "rh_stock_pairsArguments"
}
🟢rh_chain_stats

How Robinhood Chain measures from PumpPill's index, recomputed hourly with the method in the payload: tokens seen, forward-measured outcomes, how many doubled, 5x, 10x or crossed $100K, how many are stock-quoted. Quote computed_at, not the time you asked. Counts, not a success rate: entry is the market cap at logging.

輸入結構描述

{
  "type": "object",
  "properties": {},
  "title": "rh_chain_statsArguments"
}
🟢rh_whale_wallets(sort, limit)

Wallets holding 10+ ETH or $50K+ in tokens, read as on-chain balances. Tiers by dollars held (mega, whale, mini, large); positions_top names each wallet's three largest holdings. Measures who CAN move a pool, never who is right or who to follow: most listed wallets hold rather than trade (meta.trading_30d). sort='active' orders by trades.

輸入結構描述

{
  "type": "object",
  "properties": {
    "sort": {
      "default": "balance",
      "title": "Sort",
      "type": "string"
    },
    "limit": {
      "default": 25,
      "title": "Limit",
      "type": "integer"
    }
  },
  "title": "rh_whale_walletsArguments"
}
🟢rh_wallet_record(address)

One Robinhood Chain wallet's holdings and trades off the chain's own feed. A sell's size is derived from the router's minimum-out, so it is a floor, never profit. Many addresses on this chain are routing contracts, not people.

輸入結構描述

{
  "type": "object",
  "properties": {
    "address": {
      "title": "Address",
      "type": "string"
    }
  },
  "required": [
    "address"
  ],
  "title": "rh_wallet_recordArguments"
}
🟢rh_early_wallets(limit)

Robinhood Chain wallets whose first buy landed in the early window of tokens that later crossed $100K, with the feed's base rate (meta.early_base_rate) beside every rate. A record is a fact about timing, not a forecast; quote a wallet's rate only with the base rate. Wallets are removed for spraying, underperforming the base rate, or silence.

輸入結構描述

{
  "type": "object",
  "properties": {
    "limit": {
      "default": 25,
      "title": "Limit",
      "type": "integer"
    }
  },
  "title": "rh_early_walletsArguments"
}
🟢sol_early_wallets(limit)

Solana wallets recorded among a token's first buyers on tokens whose peak later reached 5x the scan cap, with the base rate (meta.base_5x, about one in twenty) beside every rate. Sprayers, at-or-below-base and silent wallets are removed with the reason. Wallet identity showed no out-of-sample edge on Solana: this answers who was early, not who to copy.

輸入結構描述

{
  "type": "object",
  "properties": {
    "limit": {
      "default": 25,
      "title": "Limit",
      "type": "integer"
    }
  },
  "title": "sol_early_walletsArguments"
}
🟢sol_token_detail(mint)

Any Solana token by mint (base58): holders, bundled-launch read, what the deployer still holds, socials, and meta.verdict, one sentence on whether it trades, can be sold, what the dev holds and how far it has run. Start from the verdict; the rest is evidence. A clean read is not a reason to buy.

輸入結構描述

{
  "type": "object",
  "properties": {
    "mint": {
      "title": "Mint",
      "type": "string"
    }
  },
  "required": [
    "mint"
  ],
  "title": "sol_token_detailArguments"
}
🟢outcomes_measured

Forward-measured outcomes across both chains: the share of logged tokens that doubled, reached 5x, 10x, or never moved. Entry is the market cap at the MOMENT OF LOGGING, never backfilled, and losers are in the denominator: a population measurement, not a track record. Recomputed hourly; a call during the recompute may take 45s or answer error='recomputing', and a retry a minute later is instant.

輸入結構描述

{
  "type": "object",
  "properties": {},
  "title": "outcomes_measuredArguments"
}
🟢exit_check(address)

Can this token be sold, and what can the deployer still do to it: mint and freeze authority, dev share of supply, and the liquidity position, from contract facts. Open to everyone, cache-only. have_record=false means no read, not safe. Fields are null when unknown rather than guessed. Facts, not advice.

輸入結構描述

{
  "type": "object",
  "properties": {
    "address": {
      "title": "Address",
      "type": "string"
    }
  },
  "required": [
    "address"
  ],
  "title": "exit_checkArguments"
}
🟡rh_scan_now(address)

MEMBERS: read one Robinhood Chain contract FRESH, when rh_token_safety said found=false or the stored read is stale. Needs a PumpPill membership: send Authorization: Bearer <claim>, the sign-in token on pumppill.org/premium. Slow (10-20s cold; do not retry). Capped per member and per day; the answer reports the budget and a refusal names the cap and its reset (00:00 UTC). A read from the last few minutes is served from the store without spending. Not idempotent: each call may spend the cap.

輸入結構描述

{
  "type": "object",
  "properties": {
    "address": {
      "title": "Address",
      "type": "string"
    }
  },
  "required": [
    "address"
  ],
  "title": "rh_scan_nowArguments"
}
🟢premium_calls_recent(limit, hours)

MEMBERS: the premium call table, the Solana tokens PumpPill logged for members, newest first, with the market cap at logging and the move since. Needs a PumpPill membership: send Authorization: Bearer <claim>, the sign-in token on pumppill.org/premium. Each row cleared an attention filter (a promoter with real reach, or a moving narrative): a filter on attention, not a prediction or a recommendation. Narrative and trend columns are deliberately withheld.

輸入結構描述

{
  "type": "object",
  "properties": {
    "limit": {
      "default": 25,
      "title": "Limit",
      "type": "integer"
    },
    "hours": {
      "default": 24,
      "title": "Hours",
      "type": "integer"
    }
  },
  "title": "premium_calls_recentArguments"
}
🟢my_watched_wallets(days)

MEMBERS: the Robinhood Chain wallets this member follows: capital (what each can move), record (counts beside the chain's base rate), activity in the window, and the events that fired. Needs a PumpPill membership: send Authorization: Bearer <claim>, the sign-in token on pumppill.org/premium. Capital is size, not correctness; a rate is never shipped without its denominator. No activity means not seen moving, not gone quiet; sell sizes are floors, never profit.

輸入結構描述

{
  "type": "object",
  "properties": {
    "days": {
      "default": 7,
      "title": "Days",
      "type": "integer"
    }
  },
  "title": "my_watched_walletsArguments"
}
🟡x_chatter(contract)

MEMBERS: what X has been saying about one contract: posts naming the address in their text, distinct accounts, combined reach, acceleration, and each poster's record on earlier calls. Needs a PumpPill membership: send Authorization: Bearer <claim>, the sign-in token on pumppill.org/premium. Reads X live before answering when the hourly budget allows (the live field says); the stored corpus is always underneath. A SAMPLE of X: zero means PumpPill saw none, and silence on an EVM contract is normal. Counts, reach and record; no sentiment or hype score. Each call may spend a live-read budget.

輸入結構描述

{
  "type": "object",
  "properties": {
    "contract": {
      "title": "Contract",
      "type": "string"
    }
  },
  "required": [
    "contract"
  ],
  "title": "x_chatterArguments"
}
🟢membership_status

Whether the claim this client sends is an active PumpPill membership, its tier, and when it renews. An unauthenticated call answers signed_in=false, not an error. Nothing about the claim itself is returned.

輸入結構描述

{
  "type": "object",
  "properties": {},
  "title": "membership_statusArguments"
}
🟢search(query)

Find PumpPill's read for a query: a Robinhood Chain address (0x + 40 hex), a Solana mint (base58), or a ticker such as HOOD. Returns ids for fetch. For a ticker the result is the one contract that clears the gate (alive, $10K+ pool, not flagged HIGH or CRITICAL) with the count of others using the name. No results is an honest miss, not a clean bill. Identifiers only, not questions.

輸入結構描述

{
  "type": "object",
  "properties": {
    "query": {
      "title": "Query",
      "type": "string"
    }
  },
  "required": [
    "query"
  ],
  "title": "searchArguments"
}
🟢fetch(id)

Fetch one result by the id search returned (rh:<address> or sol:<mint>). Returns the stored read as text with its citation and as-of time. Never triggers a scan; a missing read says so.

輸入結構描述

{
  "type": "object",
  "properties": {
    "id": {
      "title": "Id",
      "type": "string"
    }
  },
  "required": [
    "id"
  ],
  "title": "fetchArguments"
}

社群

為此伺服器評分

證據

近期觀測

已驗證未記錄版本20 個工具
已驗證未記錄版本10 個工具