Alpaca Trading API integration for Model Context Protocol (MCP)
Nothing to run from here
pumpdata is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
96/100
tool-list score
8
tools declared
remote
at its publisher
—
calls last 7d
What it does
Check a pump.fun coin, dev or wallet: deployer record, bundle, PnL. Every pump.fun trade, ever.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http pumpdata-mcp https://pumpdata.fun/mcp
# 2 — ask your agent for something these tools do
# stats, base_rate, wallet_records and 5 more
pumpdata costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
PUAll 1 server
pumpdata1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
Claude Codedeclared by this listing
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http pumpdata-mcp https://pumpdata.fun/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it answers at its publisher’s own address: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
What you approve
8 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Free. Yesterday on pump.fun (one UTC day), or any day kept: coins launched and graduated, 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. checks lists any number that failed a sanity check:
| Parameter | Type | Required | Notes |
|---|---|---|---|
| day | string | no | a UTC day, YYYY-MM-DD; default the latest |
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
| Parameter | Type | Required | Notes |
|---|---|---|---|
| band | string | yes | 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 | string | yes | window start, ISO 8601 UTC |
| to | string | yes | 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 | no | default any |
| payment | string | no | 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 |
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 addres
| Parameter | Type | Required | Notes |
|---|---|---|---|
| addresses | array | yes | base58 wallet addresses |
| mint | string | no | optional: the coin they are buying; a wallet with no record before its creation is 'new' |
| payment | string | no | 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 |
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,
| Parameter | Type | Required | Notes |
|---|---|---|---|
| mint | string | yes | the coin's mint address (base58) |
| payment | string | no | 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 |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| address | string | yes | the deployer's wallet address (base58) |
| payment | string | no | 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 |
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
| Parameter | Type | Required | Notes |
|---|---|---|---|
| mint | string | yes | the coin's mint address (base58) |
| limit | integer | no | comparables to return, default 10 |
| payment | string | no | 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 |
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. Th
| Parameter | Type | Required | Notes |
|---|---|---|---|
| picks | array | yes | up to 500 a run for now; split the rest into another run |
| latency_s | number | no | seconds from the decision to the fill |
| bankroll_sol | number | no | SOL at risk at once; a pick with no room is skipped |
| exit | object | no | take (x the entry), trail (share off the high), hold_s (seconds); any combination |
| payment | string | no | 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 |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | the id from replay |
Free
$0 forever
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install pumpdata or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATool-list grade · score 96 / 100
Release 0.3.2 · scanned 28 Oct 2026
Graded from the tools this server lists, not from its source code.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score96
Findings0 threat · 0 capability
Capabilityminimal
Coveragemanifest
Verificationnot in this report
Surface digest5000b695b88b4a4994b66dea48aad0ad7a9971228181a9014e37e7000ed0aa4b
Score vectorthreat 100 → client 96
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
Tool surfaceread
Implementation sourcenot available
Package metadatanot available
Live transportnot available
The implementation source was not read — this reflects the declared tool metadata only.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| stats | no tags | |
| base_rate | no tags | |
| wallet_records | no tags | |
| launch_record | no tags | |
| deployer_record | no tags | |
| similar_launches | no tags | |
| replay | no tags | |
| replay_result | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest5000b695b88b4a49
Scanned2026-10-28
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 0.3.2.
0.3.2
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish pumpdata can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.