mcp-server-madeonsol

⚡ Install via Smithery · 🤖 Use in Claude Desktop · 🖱️ Use in Cursor · 📚 API docs · 💰 Free API key · 🔎 On Glama

MCP server for MadeOnSol Solana KOL intelligence API. Use from Claude Desktop, Cursor, or any MCP-compatible client.

Real-time Solana trading intelligence: track 1,069 KOL wallets with <3s latency on paid keys and x402 pay-per-call (free-tier live feeds are 5-min delayed), score 23,000+ Pump.fun deployers, surface deshred deploy signals ~500ms before on-chain confirmation, detect multi-KOL coordination, surface bundle-cohort holdings (which same-slot wallets still hold a token's supply), verify any wallet's CURRENT on-chain holdings straight from its token accounts, and stream every DEX trade across 9+ programs. Free tier: 200 requests/day across 40+ endpoints (live feeds 5-min delayed) — no signup payment. Get a key at madeonsol.com/pricing.

New in 1.27.0 — top traders, sniper watchlist management, and two update tools (104 tools total). Six additions found by an internal agentic-infra coverage audit. madeonsol_token_top_traders (GET /tokens/{mint}/top-traders, PRO/ULTRA) ranks a token's wallets by realized PnL or ROI, enriched with KOL/alpha-wallet identity — this endpoint already existed on the REST API and x402 rail but had no MCP tool. madeonsol_sniper_watchlist_list / _add / _remove (PRO+/ULTRA) manage your custom sniper-deploy watchlist (madeonsol_sniper_recent(watchlist: true) narrows to it) — previously only reachable via raw HTTP. madeonsol_update_webhook (PATCH) changes a webhook's URL, events, or active state without deleting and recreating it. madeonsol_wallet_tracker_relabel (PATCH) renames or clears a tracked wallet's label.

New in 1.26.0 — deployer reputation as-of a date, and creator-fee rewards. Two new tools (PRO+, keyed msk_ API only — no x402 route). madeonsol_deployer_as_of binds GET /deployer-hunter/{wallet}/as-of: the deployer's reputation exactly as it stood on date (default today, UTC) — the latest write-on-change snapshot at or before it, so an agent backtests without look-ahead bias. snapshot.snapshot_date can predate date (write-on-change); snapshot.carried: true marks that. No snapshot at or before date → as_of: false, snapshot: null — nothing is ever synthesized. date must be ≥ 2026-04-07 and not in the future. madeonsol_deployer_rewards binds GET /deployer-hunter/{wallet}/rewards: pump.fun creator-fee rewards, answered two ways that are never merged — collected (what actually reached the wallet: direct vault claims kept 90 days, social-handle claims, shareholder payouts on any token) and attributed (every payout on the tokens it deployed, split to_self/to_others + redirected_pct). Every money field is {sol, usdc, usd}; usd is null (never a silent 0) when a SOL amount exists and no SOL price was available. top_tokens/top_recipients (≤10, USD-sorted) show where attributed fees went. Works for non-deployers too (is_deployer: false, attributed empty).

New in 1.25.0 — token surges & revivals: momentum fires with the honest half attached. The new madeonsol_tokens_surges tool binds GET /tokens/surges (PRO+, keyed msk_ API only — no x402 route): every token momentum fire, newest first. Two kinds, one row shape. surge — a token < 30 min old whose market cap runs hard against its launch MC, in three tiers that each fire at most once per mint: early (≤10 min, ≥$12k, ≥3× launch), strong (≤30 min, ≥$30k, ≥6× launch and ≥2× the lowest sample of the last 3 min — it is climbing now), breakout (≤2 min, ≥$45k, ≥8×). A tier must be sustained (current tick and a sample ≥10 s older; nothing fires before 20 s of age) — a same-slot bundle marked to $475k at age 1 s is a spike, not a surge. revival — a token with no 1-minute trade candle for ≥24 h that starts trading again, confirmed only by the tape (≥5 buys, ≥$500 buy volume, MC ≥1.5× the pre-dormancy close), never by the price mark; tier is null. Hard gates on both: liquidity ≥$1.5k and ≥2 % of MC, and the MC gained must be paid for by buy volume (a price mark in a spoof pool moves MC on ~$0). Every row carries the burst tape (source candles / wallet_trades; unique_buyers only where the mint is in trade coverage — wallet_data_available:false otherwise, never an inferred zero), kol buyers, the first-20 early_buyers cohort (bundled / sold / sniper wallets), deployer reputation and risk_flags[] (bundled_launch, few_buyers, wash_pattern, thin_liquidity, cold_deployer, sniper_heavy, early_buyers_exiting, sell_pressure, no_tape_trades, no_prior_price, mint_authority_active, transfer_fee — empty means no flag raised, not verified clean). Rows ≥65 min old carry the +1 h outcome; stats=1 prints per-(kind, tier) hit-rates (up_1h_pct, median_peak_multiple, doubled_1h_pct) — out-of-sample by construction. Filters kind, tier, mint, launchpad, deployer_tier, min_mc_usd / max_mc_usd, min_buys, exclude_flags, only_clean; cursors since / before. Pushed live on the new token:surges WS channel (events token:surge / token:revival; subscribe filters kinds[], tiers[], launchpads[], exclude_flags[], min_mc_usd / max_mc_usd, deployer_tier[]) and accepted by madeonsol_create_webhook as events token:surge / token:revival with the same filters. The response echoes the live thresholds in definitions.

New in 1.24.1 — stream tokens never expire. madeonsol_stream_token (POST /stream/token) now returns the same token on every call, forever. It stops working only if your subscription lapses or you call the tool with rotate: true to replace it (the previous value keeps working for 60 s). expires_at and the new next_refresh_at are always null (kept for wire compatibility — do not schedule refreshes on them); the response gains rotated (boolean) and lifetime (string). The server never rotates on its own and never sends token_refresh unless you rotated; a 4001 close means "mint again" (lapsed or rotated), never a timer. Prefer Authorization: Bearer <token> on the WebSocket handshake — ?token= still works and is masked in access logs.

New in 1.24.0 — token locks & vesting, upcoming unlocks, and pump.fun creator-fee sharing / claims. Five new tools (all PRO+, keyed msk_ API only — no x402 route). madeonsol_token_locks binds GET /tokens/{mint}/locks: every on-chain lock / vesting contract on a mint (Streamflow, Jupiter Lock, Bonfida vesting) with the schedule, the terms (cancelable_by_sender = the locker can pull it — funds are locked against the recipient, not the locker) and a live-derived view (locked_*, claimable_*, next_unlock) plus a summary with 7d / 30d forward unlock totals. madeonsol_token_locks_feed (GET /tokens/locks) is the cross-token feed of NEW contracts (cursor pagination.next_since, or push on WS channel token:locks), madeonsol_token_unlocks (GET /tokens/unlocks) lists upcoming unlock EVENTS (cliff / period / final / tranche) inside a 1h–90d window sorted by soonest / largest_usd / largest_pct. LP locks are not included — token/vesting locks only. madeonsol_token_fee_shares (GET /tokens/{mint}/fee-shares) decodes a pump.fun coin's on-chain SharingConfig — shareholders with share_bps, is_admin, is_social_pda (fees earmarked for an X identity: social.platform 2 = X, user_id = the numeric platform id, not the handle), redirected_bps, is_default: true = 100% to the creator — plus a distributions rollup and config history; madeonsol_token_fee_claims (GET /tokens/fee-claims) is the fee-event feed (distribution with per-address payouts[], social_claim, shares_created/updated/reset, creator_transferred, creator_claim only when asked via type=), pushed on WS channel token:fee_claims. Fee-event history starts 2026-08-17. All base-unit amounts are digit strings; ui / usd / pct are null when decimals or price are unknown.

New in 1.23.0 — live holder census: exact holder count, labelled holders, and pools that are named, not just excluded. The new madeonsol_token_holders tool binds GET /tokens/{mint}/holders (PRO+): every token account of the mint read from the ledger at confirmed and merged per owner, so concentration.holder_count is EXACT (distinct non-zero owners minus pools / bonding curves / burns) — never a trade-derived estimate; it is null only when the provider refuses the census for a mega-cap, in which case you get the top-20 view and source.census_fallback_reason says so. Each disclosed owner carries our labels (deployer / kol / early_buyer / bundle / bot / dump_cluster — empty means unknown to us, not clean), and excluded[] NAMES what was taken out of the circulating denominator: reason = pool (with dex + pool_address), bonding_curve (pump.fun / LaunchLab), burn, or program_account only when we genuinely cannot attribute the PDA; pool_pct / burned_pct / program_pct split the exclusion. Amounts are raw u64 strings. Disclosure: PRO ranks 1–10, ULTRA 1–50, BUSINESS 1–100 — the maths is tier-independent. Big tokens take 5–30 s upstream: you get 503 holder_scan_in_progress with retry_after_seconds: 20 while the scan finishes into the cache, and the retry is instant.

New in 1.22.0 — two prices on the trade tape, and the right one is now the default. The trade tape now tells you what a trade actually cost. price_sol/price_usd on each trade are THIS trade's executed price — sol_amount / token_amount, reconciling exactly with the amounts on the same row and with the PnL endpoints. Because sol_amount is the wallet's net SOL movement, that is the trader's all-in effective rate: swap fee and any account rent included, not the pool mid. The market-cap tracker's canonical pool price moved to the new market_price_sol/market_price_usd fields — it is sampled once per token per pool update, so every trade in the same slot shares it. Until now price_sol carried that canonical value and disagreed with the row's own amounts by a 7.9% median (p90 ~74%): a stale market price reads low in a pump and high in a dump, so anything you averaged out of the tape inherited the bias instead of cancelling it. Use price_sol for cost basis, fills and PnL; market_price_sol for a per-token series independent of trade size and direction. Both madeonsol_token_trades and madeonsol_wallet_trades carry all four fields, and both tool descriptions spell out which price to use so an agent does not average the wrong one.

New in 1.21.0 — the Deployer Hunter surface completed. Seven new operations that existed on the API but had no SDK binding: madeonsol_deployer_leaderboard, madeonsol_deployer_stats, madeonsol_deployer_profile, madeonsol_deployer_tokens, madeonsol_deployer_alert_stats, madeonsol_deployer_best_tokens and madeonsol_deployer_recent_bonds. Read bonding_rate (lifetime) against recent_bond_rate (rolling) — the gap between them is the signal, not either number alone. runner_rate only means something once labeled_tokens >= 3, and an untracked wallet returns a profile with zeroed counters, not a 404, so check total_deployed before reading a 0% bond rate as a track record. Dependency ranges are now bounded to the versions actually tested (@x402/* ^2.x, @solana/kit ^5.5.1) instead of open-ended >=0.0.1, and the lazily-imported x402 peers are marked optional — a keyed install no longer pulls the whole Solana stack.

New in 1.20.0 — Token depth / price impact + deployer self-activity on risk. New tool madeonsol_token_depth (GET /tokens/{mint}/depth) — per-pool price-impact / slippage: "how much SOL moves this token's price N%", per pool (NOT router-optimal). Pass up to 8 SOL buy sizes (each >0 and ≤10000; default [0.5, 1, 5, 10]); every computable pool returns spot_price_sol, fee_pct, a quotes[] entry per size (size_sol, tokens_out, avg_price_sol, price_impact_pct), and to_move_price — the SOL required to move price 1% / 5% / 10%. Constant-product AMMs are served from stream reserves (source: "stream" with reserves_age_ms); pump.fun/bonk bonding curves from a live read of the curve's virtual reserves (source: "live_rpc"). Pools that can't be priced honestly — concentrated CLMM/Orca/DLMM, Meteora-DBC curves, unclassified models — come back in unsupported_pools[] with a reason (e.g. concentrated_liquidity_depth_not_supported, curve_graduated_use_amm_pool) instead of a wrong number; primary_pool names the deepest computable pool, found: false means no pools tracked. PRO/ULTRA only. And madeonsol_token_risk now returns a top-level dev block (deployer self-activity; null when the mint has no deployer-pipeline row): the create-tx self-buy snapshot (buy_sol, buy_tokens, buy_supply_pct), the post-create rollup (bought_tokens_after — catches the same-second-separate-tx dev buy the create snapshot reads as 0 — sold_tokens, sold_sol, first_sell_at/last_sell_at), live on-chain holdings (holdings_tokens, holdings_supply_pct — pump.fun 1B denominator, null elsewhere — wallet_empty: is the dev wallet empty NOW), and transferred_out (tokens left without a sell; null = unknown, never a guess), plus as_of. deployer:alert webhook/WS payloads gain dev_buy_sol + dev_buy_supply_pct.

New in 1.19.0 — Batch wallet classification + token trade tape + bigger keyless catalog. New tool madeonsol_wallet_batch_classify — reputation flags for 1–100 wallets in one call (counts as one request): per wallet is_sniper / is_bundler / is_dumper / is_kol (+ kol_name), bot_confidence (string enum none/low/medium/high, null when not alpha-tracked), and a dump_cluster block (dump_cohorts, runner_cohorts, total_cohorts, as_of). Flags are pump.fun-pipeline scoped — false = not observed, NOT verified clean; is_bundler is lifetime, is_dumper is a rolling 42d window. New tool madeonsol_token_trades — mint-scoped cursor-paginated trade tape (the backfill complement to the live firehose): tx_signature, wallet_address, action, sol_amount, token_amount, price_sol/price_usd, early_buyer_rank, slot, block_time, traded_at; filters action / wallet / since–until (default FULL history — capture starts 2026-04-12), plus a coverage honesty block. Both PRO/ULTRA. madeonsol_wallet_stats flags gain is_sniper/is_bundler/is_dumper + dump_cluster, and bot_confidence is now correctly typed as a string enum (it was documented as a number and always came back null due to a server bug — now returns real values). madeonsol_token_risk inputs and madeonsol_sniper_recent deploys gain the slot-window sniper_footprint/footprint rollup (buys, buyers, sol, supply_pct, sniper_wallet_buys, data_available, as_of — null = not observable, not zero). The keyless x402 catalog grows 18 → 25 endpoints: token candles ($0.01), almost-bonded ($0.01), top-traders ($0.02), cap-table ($0.02), sniper recent ($0.01), token flow ($0.01), deployer trajectory ($0.01) — madeonsol_sniper_recent and madeonsol_deployer_trajectory now work keyless via x402 too.

New in 1.18.0 — Verified on-chain wallet holdings. New tool madeonsol_wallet_holdings — the wallet's CURRENT holdings read straight from chain: its actual SPL + Token-2022 token accounts and SOL balance, each enriched with our price_usd / value_usd / market_cap_usd / name / symbol / is_bonded, plus transfer_delta (on-chain amount − trade-derived net position — exposes non-swap flows like airdrops, insider funding, and wallet-hopping). Distinct from madeonsol_wallet_positions (trade-derived FIFO): this is what the wallet actually holds right now. Params: limit (1–500, default 200), min_value_usd (default 0). Returns { address, sol_balance, holdings[], summary, verified_at, trade_window_days, cache_hit, ttl_seconds }. ULTRA only.

New in 1.17.0 — Bundle-cohort holdings. New tool madeonsol_token_bundle — which same-slot "bundle" wallets bought a token and how much of supply they still hold (the incumbents' "current held %" rug/insider signal, from confirmed on-chain data). Returns a bundle block (wallet_count, bundle_kind atomic_tx/same_slot/none, held_ratio, held_pct_of_supply — the headline, net held / circulating supply, null if unknown — fully_exited, buy_volume, tokens_held) plus a wallets[] array (rank, wallet, held_ratio, has_sold, atomic, is_kol). BASIC get the bundle block only (empty wallets[]); PRO adds top-10 flags-only wallets; ULTRA returns the full cohort with enriched identities (kol_name, win_rate, bot_confidence, tokens_held).

New in 1.16.0 — Batch risk scoring + live stream-session control. New tool madeonsol_tokens_batch_risk — bulk rug-risk/safety scoring for up to 50 mints in one call, returning the same per-mint shape as madeonsol_token_risk (0–100 score, band, explainable factors[], raw inputs) plus an as_of timestamp; untracked mints come back as { mint, error: "not_tracked" } without failing the batch, and the whole call counts as one request against quota. Plus two WebSocket session tools: madeonsol_stream_sessions_list (list your live sessions — id, service, tier, channels, connected_at, remote_ip, messages_sent) and madeonsol_stream_session_kill (force-disconnect a session by id to free its connection slot, e.g. a ghost socket). PRO/ULTRA only.

New in 1.15.0 — Almost-bonded discovery + trending sorts. New tool madeonsol_almost_bonded — pre-bond pump.fun tokens near graduation, ranked by velocity (Δprogress/min): "95% and accelerating" beats "92% stalled". Each token carries progress_pct, velocity_pct_per_min, eta_minutes, stalled, real_sol_reserves, market_cap_usd, liquidity_usd, authorities_revoked, deployer_tier, and age_minutes. Params: min_progress, max_progress, min_velocity_pct_per_min, max_age_minutes, deployer_tier, authority_revoked, min_liq, sort (velocity_desc / progress_desc / eta_asc), limit. PRO/ULTRA only. Plus madeonsol_tokens_list gains four momentum sorts — mc_change_5m_desc, mc_change_1h_desc, volume_1h_desc, and trending (composite recent-volume × positive-momentum rank).

New in 1.14.0 — Token trade flow. New tool madeonsol_token_flow — a trade-flow aggregate (organic-vs-fake volume) over a 1h/24h window: unique_wallets / unique_buyers / unique_sellers, buy_count / sell_count / total_trades, buy_sol / sell_sol / net_sol (sell − buy; positive = net SOL leaving the pool), and trades_per_wallet (wash-trading proxy). PRO/ULTRA only. Deployer alerts (madeonsol_deployer_alerts) now carry deployers.deployer_sol_balance — the deployer wallet's SOL balance at alert time (null for historical rows).

New in 1.13.0 — Token OHLCV candles. New tool madeonsol_token_candles — historical price candles (1m/5m/15m/1h/4h/1d) aggregated from the on-chain trade firehose. Each candle has t/open/high/low/close/volume_usd/trades/market_cap_usd. PRO returns OHLCV for the last 30 days; ULTRA adds buy/sell volume + count splits, net flow, MEV volume, open/close liquidity, high/low MC, and full history. PRO/ULTRA only.

New in 1.12.0 — Token risk score. New tool madeonsol_token_risk — a transparent 0–100 rug-risk/safety score (higher = riskier) with a band (safe/caution/danger), an explainable factors[] array, and the raw inputs (mint/freeze authority, liquidity, liq-to-MC ratio, transfer fee, launch cohort, deployer bond rate, KOL signal, blacklist). PRO/ULTRA only.

New in 1.11.0 — madeonsol_tokens_list gains three new filter params: min_liq_mc_ratio, max_liq_mc_ratio, and deployer_tier. Response items now include liquidity_to_mc_ratio and deployer_tier. New tool: madeonsol_signal_performance — evaluate signal efficacy (hit rate, sample size, median outcome) before acting on any signal. KOL leaderboard entries now include median_hold_minutes_30d and percentile_early_entry_30d.

New in 1.10.4 — Deployer alerts/profiles now expose runner_rate + labeled_tokens (fraction of a deployer's labeled tokens that ran vs dumped, gate on labeled_tokens ≥3) plus avg_time_to_bond_minutes.

New in 1.10.3 — Dump-cluster detection. madeonsol_token_buyer_quality breakdown now includes dump_cluster_count (3+ dump-cluster wallets in the first-20 → 94% historical dump rate vs 61% base) and recycled_early_buyer_count. Full breakdown is returned on all tiers. Also: the API now pushes every pump.fun graduation in real time (token:graduations WS channel).

New in 1.10 — Deshred Sniper Alerts. madeonsol_sniper_recent surfaces pump.fun deploys from shred-level data ~500ms before on-chain confirmation. PRO: elite/good deployers. ULTRA: all tiers + custom watchlist. Use sniper:deploys WebSocket or sniper:deploy webhook for live push.

New in 1.9 — Price alerts, scout leaderboard, coordination history. madeonsol_price_alerts_* CRUD (PRO=5, ULTRA=25). madeonsol_scout_leaderboard ranks top scouts by first-touch follow-on rate. madeonsol_coordination_history and madeonsol_peak_history expose the historical record. madeonsol_wallet_stats now returns derived: win_rate, roi, verdict, biggest_miss.

New in 1.8 — Universal Wallet API. madeonsol_wallet_stats, madeonsol_wallet_pnl, madeonsol_wallet_positions, madeonsol_wallet_trades — FIFO cost-basis PnL and cursor-paginated raw trades for any Solana wallet. PRO+. Cache hits don't count against quota.

New in 1.7.0 (2026-05-12) — Two new tools: madeonsol_me (account/quota introspection — read tier, remaining requests, and per-feature usage without parsing rate-limit headers) and madeonsol_tokens_list (PRO+ filtered, sortable token directory — MC band, liquidity floor, primary DEX, authority/safety flags, plus computed 1h volume / MEV-share / MC-change deltas). Token responses now expose velocity / MEV-share fields. Token directory defaults to min_liq=2000 to skip phantom-MC dust — pass min_liq=0 to opt out. /token/{mint} now returns structured 400 errors (code / reason / example / docs) instead of plain strings. Deprecated avg_entry_mc_usd field fully removed from KOL/alpha leaderboards.

Install via Smithery (one line)

Smithery is the easiest path — it writes the config for you and handles the install: