# PumpPill — token safety and measured outcomes (remote · api.pumppill.org)

Token safety, deployer history, whale balances and measured outcomes on Robinhood Chain and Solana

- Trust score: 71/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-26

## Components

- remote · `api.pumppill.org`: 71/100 (this document), [markdown](https://verifymcp.io/servers/org-pumppill-token-safety/api.md), [page](https://verifymcp.io/servers/org-pumppill-token-safety/api)

## Channel facts

- Endpoint: `https://api.pumppill.org/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.2.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-26.

- **Endpoint Security**: 74/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 86/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 2245 tokens (~106/item across 21 items; 20 tools + 1 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 7/100
  - Stability observed for 2 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 67/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 20 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 22 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the PumpPill — token safety and measured outcomes MCP server?

PumpPill — token safety and measured outcomes is a hosted endpoint at https://api.pumppill.org/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http org-pumppill-token-safety 'https://api.pumppill.org/mcp'
```

### Cursor

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

### VS Code

```json
{
  "servers": {
    "org-pumppill-token-safety": {
      "type": "http",
      "url": "https://api.pumppill.org/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.org-pumppill-token-safety]
url = "https://api.pumppill.org/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "org-pumppill-token-safety": {
      "type": "remote",
      "url": "https://api.pumppill.org/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add org-pumppill-token-safety --url 'https://api.pumppill.org/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  org-pumppill-token-safety:
    url: "https://api.pumppill.org/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "org-pumppill-token-safety": {
      "Transport": "http",
      "Url": "https://api.pumppill.org/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add org-pumppill-token-safety -t streamable-http -u 'https://api.pumppill.org/mcp'
```

### Other

```json
{
  "mcpServers": {
    "org-pumppill-token-safety": {
      "type": "http",
      "url": "https://api.pumppill.org/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-26 (score 71, +1)

- [security] Tool “membership_status” rewrote its description, which is the text the model reads
- [security] Tool “my_watched_wallets” rewrote its description, which is the text the model reads
- [security] Tool “outcomes_measured” rewrote its description, which is the text the model reads
- [security] Tool “premium_calls_recent” rewrote its description, which is the text the model reads
- [security] Tool “rh_chain_stats” rewrote its description, which is the text the model reads
- [security] Tool “rh_deployer_record” rewrote its description, which is the text the model reads
- [security] Tool “rh_early_wallets” rewrote its description, which is the text the model reads
- [security] Tool “rh_flagged_recent” rewrote its description, which is the text the model reads
- [security] Tool “rh_stock_pairs” rewrote its description, which is the text the model reads
- [security] Tool “rh_ticker_resolve” rewrote its description, which is the text the model reads
- [security] Tool “rh_token_safety” rewrote its description, which is the text the model reads
- [security] Tool “rh_wallet_record” rewrote its description, which is the text the model reads
- [security] Tool “rh_whale_wallets” rewrote its description, which is the text the model reads
- [security] Tool “sol_early_wallets” rewrote its description, which is the text the model reads
- [security] Tool “sol_token_detail” rewrote its description, which is the text the model reads
- [security] Tool “x_chatter” rewrote its description, which is the text the model reads
- [functional improvement] Schema quality: 168 → 106
- [functional] Server version: 1.1.0 → 1.2.0
- [functional] New tool “exit_check”
- [functional] New tool “fetch”
- [functional] New tool “rh_scan_now”
- [functional] New tool “search”

### 2026-09-25 (score 70, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-09-24 (score 69)

First indexed and scored.

## MCP tools (20)

### `rh_token_safety` (~105 tokens)

Robinhood Chain token safety read

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.

Input parameters:

- `address` (string, required)

### `rh_ticker_resolve` (~76 tokens)

Which contract is the real ticker

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.

Input parameters:

- `symbol` (string, required)

### `rh_deployer_record` (~79 tokens)

Robinhood Chain deployer history

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.

Input parameters:

- `address` (string, required)

### `rh_flagged_recent` (~75 tokens)

Recently flagged Robinhood Chain tokens

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.

Input parameters:

- `limit` (integer)

### `rh_stock_pairs` (~77 tokens)

Memecoins paired with a tokenized 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.

Input parameters:

- `stock`

### `rh_chain_stats` (~88 tokens)

Robinhood Chain statistics

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.

### `rh_whale_wallets` (~109 tokens)

Wallets large enough to move a Robinhood Chain pool

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.

Input parameters:

- `limit` (integer)
- `sort` (string)

### `rh_wallet_record` (~66 tokens)

One Robinhood Chain wallet's holdings and trades

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.

Input parameters:

- `address` (string, required)

### `rh_early_wallets` (~96 tokens)

Robinhood Chain wallets that were early on winners

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.

Input parameters:

- `limit` (integer)

### `sol_early_wallets` (~102 tokens)

Solana wallets that were early on winners

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.

Input parameters:

- `limit` (integer)

### `sol_token_detail` (~88 tokens)

Solana token detail

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.

Input parameters:

- `mint` (string, required)

### `outcomes_measured` (~103 tokens)

What the tokens PumpPill logged actually did

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.

### `exit_check` (~82 tokens)

Can this be sold, and can the dev still rug it

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.

Input parameters:

- `address` (string, required)

### `rh_scan_now` (~136 tokens)

Scan a Robinhood Chain contract now (members)

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.

Input parameters:

- `address` (string, required)

### `premium_calls_recent` (~120 tokens)

PumpPill premium calls (members)

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.

Input parameters:

- `hours` (integer)
- `limit` (integer)

### `my_watched_wallets` (~119 tokens)

My watched wallets (members)

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.

Input parameters:

- `days` (integer)

### `x_chatter` (~146 tokens)

X chatter on a contract (members)

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.

Input parameters:

- `contract` (string, required)

### `membership_status` (~53 tokens)

PumpPill 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.

### `search` (~115 tokens)

Search PumpPill's index

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.

Input parameters:

- `query` (string, required)

### `fetch` (~57 tokens)

Fetch one PumpPill read

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.

Input parameters:

- `id` (string, required)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/org-pumppill-token-safety/api#diagnostics

## Score history

- 2026-09-26: 71
- 2026-09-25: 70
- 2026-09-24: 69

## Common questions

### What is the PumpPill — token safety and measured outcomes MCP server?

PumpPill — token safety and measured outcomes is an MCP server listed in the public MCP registry as org.pumppill/token-safety. Token safety, deployer history, whale balances and measured outcomes on Robinhood Chain and Solana. This page covers its hosted endpoint (https://api.pumppill.org/mcp).

### Is the PumpPill — token safety and measured outcomes MCP server safe to use?

PumpPill — token safety and measured outcomes scores 71 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the PumpPill — token safety and measured outcomes MCP server expose?

PumpPill — token safety and measured outcomes exposes 20 tools: rh_token_safety, rh_ticker_resolve, rh_deployer_record, rh_flagged_recent, rh_stock_pairs, and 15 more. Their descriptions and schemas cost roughly 1,892 tokens of context every time the server is loaded.

### Does the PumpPill — token safety and measured outcomes MCP server require authentication?

No. We connected to PumpPill — token safety and measured outcomes without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the PumpPill — token safety and measured outcomes MCP server still maintained?

PumpPill — token safety and measured outcomes is still listed as active in the MCP registry. We last reached this channel on 26 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://api.pumppill.org/mcp
- Website: https://www.pumppill.org/for-agents
- Changelog RSS feed: https://verifymcp.io/servers/org-pumppill-token-safety/api.xml
- Changelog JSON feed: https://verifymcp.io/servers/org-pumppill-token-safety/api.json
- HTML version of this page: https://verifymcp.io/servers/org-pumppill-token-safety/api