# pumpdata

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

- name: fun.pumpdata/pumpdata
- version: 0.3.1
- connection class: R0 (autonomous)
- trust: 96/100
- quality: 73/100 (new)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/fun.pumpdata%2Fpumpdata
- tools: https://api.protogrid.dev/v1/servers/fun.pumpdata%2Fpumpdata/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

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


## Trust

- hygiene: 100
- liveness: 100
- freshness: 100
- provenance: 85
- drivers: +repository +dns-namespace +website +reachable +uptime-100% +updated-2d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 73/100 (new)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-06-18; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 71 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- fail `tools.annotations`: no tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: stats (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); base_rate (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); wallet_records (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 1,900 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: n/a (weight 15)

- n/a `stability.changes`, `stability.rug_pull`: tool history recorded for 2 of the 7 days needed

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 8, about 1,900 tokens to load them all
- tool set hash: d21bd621aa3e4c1922352694f0bb1a56
- tools last changed: 2026-10-18T21:37:18.019Z
- badge: [![protogrid quality](https://protogrid.dev/badge/fun.pumpdata/pumpdata.svg)](https://protogrid.dev/servers/fun.pumpdata/pumpdata)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-18 `deployer_record` added
  - A pump.fun deployer'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. Facts, no score. $0.005 a call, USDC on Solana over x402.
- 2026-10-18 `similar_launches` added
  - The launches most like this one at the same age, named with their mints, 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. Not a prediction: what launches that looked like this did next. $0.005 a call, USDC on Solana over x402.
- 2026-10-18 `stats` added
  - Free. Yesterday on pump.fun (one UTC day), or any day kept: coins launched and graduated, SOL and USD volume, traders, failed transactions; who made money (top 10 wallets by net SOL, the 5 biggest losers, the share of traders down); the top coins by volume, the fastest graduations, the biggest launches; launches and the 1 h graduation rate per UTC hour; launches dead by their second hour; the busiest deployers. `summary` is one paragraph to quote. Each wallet and coin names the paid call that goes deeper (wallet_records, launch_record).
- 2026-10-17 `replay` changed (description)
  - before: Your picks, replayed honestly. Picks with timestamps and sizes in; what they made, pick by pick and in sum, every coin in the window counted including the dead ones, filled at the pool as it stood after your latency, with every fee, the fixed costs and the bankroll you set. 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.
  - after: Your picks, replayed honestly. 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. 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.
- 2026-10-17 `wallet_records` changed (description)
  - before: What these wallets have been since March 2025: for each address its class by rule (winner: took out more than it put in over 20+ coin-weeks; bot: a coin traded 20+ times in a week or 500+ coins; 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. Up to 50 addresses a call. $0.01 a call, USDC on Solana over x402.
  - after: What these wallets have been since day one: for each address its class by rule (winner: took out more than it put in over 20+ coin-weeks; bot: a coin traded 20+ times in a week or 500+ coins; 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. Up to 50 addresses a call. $0.01 a call, USDC on Solana over x402.
- 2026-10-17 `launch_record` added
  - This launch, historically. The deployer's record at this 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). $0.005 a call, USDC on Solana over x402.
- 2026-10-17 `wallet_records` added
  - What these wallets have been since March 2025: for each address its class by rule (winner: took out more than it put in over 20+ coin-weeks; bot: a coin traded 20+ times in a week or 500+ coins; 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. Up to 50 addresses a call. $0.01 a call, USDC on Solana over x402.

Full history: https://api.protogrid.dev/v1/servers/fun.pumpdata%2Fpumpdata/changes

## Remotes

- https://pumpdata.fun/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (8)

- `base_rate`: How often it happens anyway. How many coins first traded inside a market-cap band in a window, how many of those then reached 2x, 5x, 10x and 20x within 3 h, and the median peak. 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.
- `deployer_record`: A pump.fun deployer'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. Facts, no score. $0.005 a call, USDC on Solana over x402.
- `launch_record`: This launch, historically. The deployer's record at this 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). $0.005 a call, USDC on Solana over x402.
- `replay`: Your picks, replayed honestly. 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. 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.
- `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.
- `similar_launches`: The launches most like this one at the same age, named with their mints, 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. Not a prediction: what launches that looked like this did next. $0.005 a call, USDC on Solana over x402.
- `stats`: Free. Yesterday on pump.fun (one UTC day), or any day kept: coins launched and graduated, SOL and USD volume, traders, failed transactions; who made money (top 10 wallets by net SOL, the 5 biggest losers, the share of traders down); the top coins by volume, the fastest graduations, the biggest launches; launches and the 1 h graduation rate per UTC hour; launches dead by their second hour; the busiest deployers. `summary` is one paragraph to quote. Each wallet and coin names the paid call that goes deeper (wallet_records, launch_record).
- `wallet_records`: What these wallets have been since day one: for each address its class by rule (winner: took out more than it put in over 20+ coin-weeks; bot: a coin traded 20+ times in a week or 500+ coins; 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. Up to 50 addresses a call. $0.01 a call, USDC on Solana over x402.