Alpaca Trading API integration for Model Context Protocol (MCP)
MAD Synapse 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.
What it does
Solana + pump.fun intel for agents: launch verdicts, token risk, dev/wallet records, smart money.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http mad-synapse-mcp https://agent.maddegen.art/hub/mcp
# 2 — ask your agent for something these tools do
# launch_scan, token_risk, pump_launches and 12 more
MAD Synapse costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
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.
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 mad-synapse-mcp https://agent.maddegen.art/hub/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
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.
15 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.
One call, one verdict on a pump.fun launch: 0-100 score with positives and risks, graduation odds, dev record, snipers, holders, flow. Runs pump_token + pump_dev + pump_odds together (cheaper than calling them separately) and folds them into a single score and verdict an agent can act on: strong / neutral / weak / avoid. When to use: The one-call verdict on a pump.fun launch; it combines pump_toke
| Parameter | Type | Required | Notes |
|---|---|---|---|
| mint | string | yes | pump.fun token mint. Base58 Solana address, 32-44 chars. |
0-100 rug-risk score for any Solana token: mint/freeze authority, Token-2022 traps, holder concentration, liquidity depth — plus pump.fun curve flags. Contract state is read live from Solana (authorities, Token-2022 extensions such as transfer fees, hooks, permanent delegate, pausable), holders from the largest accounts, market from DexScreener. For pump.fun mints the curve forensics flags are mer
| Parameter | Type | Required | Notes |
|---|---|---|---|
| mint | string | yes | token mint. Base58 Solana address, 32-44 chars. |
The newest pump.fun tokens with dev buy, early buyers/volume, curve progress, market cap and creator launch count. Returns up to 50 of the most recent launches (seconds old) with the first-N-seconds flow already aggregated, so an agent can shortlist without replaying the chain. When to use: To discover new mints; then use launch_scan for a verdict on one of them. Price: $0.002 per call (10 free/da
| Parameter | Type | Required | Notes |
|---|---|---|---|
| limit | integer | no | How many of the newest launches to return. Range 1-50. Default 20. |
| window_s | integer | no | early-flow window after creation. Range 30-3600. Default 300. |
Live pump.fun heartbeat: trades/min, launches, graduations, graduation rate, hottest tokens in the last 15 min. Computed from our own live recording of every pump.fun bonding-curve trade. Use it to decide whether the launch market is hot or dead before scanning individual tokens. When to use: For the market right now; for trends over days use pump_history (callable here by name). Price: free. Erro
No parameter schema on file.
A creator wallet's launch history: launches, graduation rate, launch cadence, how fast the dev sells, verdict. Looks up every token the wallet created since recording began and replays the dev's own trades on its 15 most recent launches. When to use: For the creator of a token; pass the dev wallet, not the mint (pump_token (callable here by name) reports the dev of a mint). Price: $0.01 per call (
| Parameter | Type | Required | Notes |
|---|---|---|---|
| creator | string | yes | creator (dev) wallet. Base58 Solana address, 32-44 chars. |
Any wallet's pump.fun trading record: realized PnL, win rate, hold time, frequency (bot or human), tokens it launched. Analyses up to the last 20,000 curve trades of the wallet. Use it to judge whether a wallet is smart money, a sniper bot, a serial dumper or a dev. When to use: For a trader's pump.fun performance. For a quick deal/no-deal verdict on any wallet use counterparty_check; to test whet
| Parameter | Type | Required | Notes |
|---|---|---|---|
| wallet | string | yes | wallet address. Base58 Solana address, 32-44 chars. |
| limit | integer | no | How many of the wallet's most recent recorded trades to analyse. Range 100-20000. Default 20000. |
The pump.fun wallets with the best realized PnL in the last 24 h — and the tokens those wallets are buying right now. Leaderboard of wallets by realized profit on fully-closed curve positions (min 8 closed, rebuilt every 30 min), sortable by PnL, win rate or ROI, plus a live feed of what the top 50 bought in the last N minutes, ranked by how many of them piled in. When to use: To find wallets wort
| Parameter | Type | Required | Notes |
|---|---|---|---|
| limit | integer | no | How many top wallets to return. Range 1-50. Default 20. |
| window_min | integer | no | look-back for buying_now. Range 1-120. Default 15. |
| sort | string | no | Rank by realized PnL in SOL ("pnl"), win rate ("win_rate") or return on SOL spent ("roi"). Default "pnl". |
| exclude_bots | boolean | no | drop sub-20-second and high-frequency wallets. Default false. |
Would copying this wallet have made money? Replays its pump.fun entries and exits 0–25 slots late on the recorded curve and shows where the edge dies. Takes the wallet's pump.fun positions over the last 1–14 days and simulates a copier that buys the same token and sells when the leader sells, arriving 0, 1, 2, 5, 10 or 25 slots (0–10 s) late. Fills use the bonding-curve reserves our tape recorded
| Parameter | Type | Required | Notes |
|---|---|---|---|
| wallet | string | yes | leader wallet to copy. Base58 Solana address, 32-44 chars. |
| days | integer | no | How many days of the wallet's history to replay. Range 1-14. Default 3. |
| size_sol | number | no | SOL per copied entry. Range 0.01-10. Default 0.1. |
| exit | string | no | sell on the leader's first sell, or once it has sold 90%. Default "first_sell". |
| max_positions | integer | no | most recent positions to replay. Range 10-300. Default 150. |
One-call verdict on a Solana wallet before you deal with it: serial token launcher, fast dumper, trading bot, or clean. Combines the wallet's pump.fun launch history (graduation rate, how fast it sells its own launches) with its trading profile into a risk level and reasons. When to use: Before sending to or trading with a Solana wallet; for full trade stats use pump_wallet. Price: $0.005 per call
| Parameter | Type | Required | Notes |
|---|---|---|---|
| wallet | string | yes | wallet address. Base58 Solana address, 32-44 chars. |
Meteora DLMM liquidity providers ranked by measured on-chain edge: net USD, median multiple, win rate, hold time, size, recency. Produced by our own discovery engine, which decodes DLMM liquidity instructions across high-volume and high-yield pools every few hours and scores each wallet's completed round trips. These are the wallets our live copier watches. Price: $0.02 per call (10 free/day; afte
| Parameter | Type | Required | Notes |
|---|---|---|---|
| limit | integer | no | How many ranked LP wallets to return. Range 1-25. Default 10. |
USD price, 24h change and liquidity for up to 100 Solana mints; flags illiquid (dead) tokens. Jupiter price data with a liquidity floor: anything under $1,000 of liquidity is flagged dead, because round-trip quotes on dead curves look fine and are not. When to use: For Solana mints by address; for majors or other chains by symbol use crypto_price (callable here by name). Price: free. Errors: retur
| Parameter | Type | Required | Notes |
|---|---|---|---|
| mints | array | yes | Solana token mint addresses (base58) to price. 1-100 items. |
Everything a Solana wallet holds — SOL, SPL and Token-2022 tokens — valued in USD and sorted by value. Reads token accounts from both token programs and prices them in one pass. Empty accounts are counted as reclaimable rent. When to use: For Solana wallets; for EVM wallets use evm_address (callable here by name). Price: $0.003 per call (10 free/day; after that a payment-required result lists x402
| Parameter | Type | Required | Notes |
|---|---|---|---|
| wallet | string | yes | wallet address. Base58 Solana address, 32-44 chars. |
Turns any Solana transaction signature into plain facts: status, fee, programs by name, SOL and token balance changes per owner, a one-line summary. Works for swaps, pump.fun trades, LP moves, transfers and failures (includes the error log lines). When to use: For Solana signatures; for 0x hashes use evm_tx (callable here by name). Price: $0.003 per call (10 free/day; after that a payment-required
| Parameter | Type | Required | Notes |
|---|---|---|---|
| signature | string | yes | Solana transaction signature (base58, 64-90 chars). |
Who bundled a Solana pump.fun launch: every block-0 wallet labelled sniper bot / bundle / dev-linked, supply bought and still held, holders who got tokens by transfer, serial-dev check, top-10 concentration, RugCheck — plus a back-tested skip/pass verdict. The rug guard MAD snipers use before every buy. Skip rules were tested on 2,221 real caller calls (held-out: stop-outs 10%→5%, rugs 16%→11%): c
| Parameter | Type | Required | Notes |
|---|---|---|---|
| mint | string | yes | Solana token mint (pump.fun launches get the full bundle view) Base58 Solana address, 32-44 chars. |
Solana right now: TPS (total and non-vote), slot and block height, epoch progress and ETA, priority-fee percentiles, cluster version. Read from mainnet RPC: recent performance samples, epoch info, prioritization fees. When to use: For Solana fees/TPS; for EVM and BTC fee costs use gas_now (callable here by name). Price: free. Errors: returns isError with a message for invalid input or an upstream
No parameter schema on file.
- 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 MAD Synapse or to call it, at any volume.
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.
This listing is an address its publisher runs, and you connect to it directly — this marketplace is not in the path. The scanner reads packages and public source, and an address is neither. So there is no grade — not a withheld one, an unmeasured one.
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 2.2.0.
No release note was published with this version.
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.
Any signed-in account that does not publish MAD Synapse can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
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.