million MCP server
io.github.Kelows/million·v1.0.0·4 starsOperate a self-hosted Solana whale tracker and copy-trading deck: positions, rules, token checks.
4 stars39 downloads/wk
Reviews
Write oneNobody has reviewed million yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
million tools (14, 2 write)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
analyze_walletFetch a roster wallet's trading history and compute its metrics: realized PnL in SOL, win rate, hold times, per-token breakdown and flags (bot, distributor, fresh wallet). Spends Helius credits.
check_tokenwrite actionRun the deck's safety checks on a token: mint and freeze authority, liquidity, market cap, holder concentration, deployer history, Jupiter sell simulation, RugCheck. Returns PASS, WARN or FAIL with each check.
find_token_buyersSize buyers of a token, with a quick analysis preview and flags (bot, fresh wallet, cluster) for the biggest. The way to find wallets worth following. Spends Helius credits.
get_bookOpen and closed positions (paper or live) with size, entry and exit prices, PnL and exit reason, plus book statistics.
get_decisionsWhat the deck decided for recent token events from followed wallets, newest first: signals, opened positions, shadow trades and skips, each with its reason. Kept for 3 days.
get_flowsTokens the followed wallets are accumulating or distributing right now, counted per owner (clusters of wallets vote once), bots excluded, buys netted against sells.
get_roster_holdingsTokens the followed wallets still hold, ranked by distinct owners and SOL still in at cost, and where the roster realized profit on round trips it watched close.
get_rulesThe trading rules in force: which signals trade, minimum buy sizes, position sizing, exits (trailing stop, stop loss), exposure caps and risk halts.
get_statusIs the deck running, paper or live, is the live feed receiving events, how many wallets are followed, and a summary of the book (open positions, realized PnL, risk halt).
get_walletA roster wallet's stored analysis, live activity, subscription state and linked wallets of the same owner.
import_walletsAdd wallet addresses to the roster (not followed yet). Analyze them, then subscribe the ones the user picks.
set_wallet_subscriptionFollow (subscribe) or unfollow a roster wallet. Followed wallets feed the live feed and can trigger trades. Only do this when the user asked for that wallet.
update_ruleswrite actionChange some trading rule fields (use get_rules for names and current values). Only the given fields change; the deck validates and may clamp values. Applies to new signals; open positions keep their exits. Cannot switch paper to live. Returns each changed field before and after.
why_not_boughtEverything needed to explain why the deck did or did not buy one token: its decision history (routine skips included), the token's check report, any position in it, and the trading rules in force.
Public scan report
scanner v0.1.10 · 2026-10-03 · same rubric, same numbers if you re-run it
- Code scan2 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitylocal package, no credentials required12/15
- Maintenancelast push 19 days ago15/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
How million compares
Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 92/100
- higher than 93% of 48,243 servers
- Tools
- 14
- the typical server has 7
- Tools that change things
- 14%
- typical: 0%. Fewer write tools means less an agent can break
- GitHub stars
- 4
- more than 82% of 28,706 servers
- Downloads a week
- 39
- more than 29% of 12,306 servers with a package
What its tools let an agent do: 10 read · 1 create · 3 change
Install million in Claude Code, Cursor or VS Code
Runs npx -y million-mcp on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add million -- npx -y million-mcp
What the publisher says
From the million repository's README, as published. We do not edit it. Read it on GitHub
million
Your personal Solana memecoin intelligence dashboard.
An open-source, self-hosted whale tracker and copy-trading deck that you run by talking to your AI coding agent (Claude Code, Codex, Cursor, Gemini CLI…). It watches the wallets you follow, finds more wallets through the tokens they buy, filters out bots and rugs, shows where the smart money is flowing, and trades the signals that survive.
Start in two commands (Node 24 or nvm):
npx create-million # clones, installs, checks your Helius key, starts the deck
cd million && claude # or codex, gemini…, then type: set me upOr clone it yourself and let the agent do everything: git clone https://github.com/Kelows/million && cd million, open your agent and type set me up.
Without a webhook the live feed uses a websocket and follows up to 25 wallets; a webhook only lifts that cap.
Experimental. Provided as is, with no warranty. This is a research tool,
not a money printer, and nothing in it is financial advice. Trading meme coins
can lose you everything you put in. If you trade real money with it, that is
your decision and your risk: the authors are not responsible for any loss.
Talk to it: million is the engine, your AI agent is the operator
You don't need to know what a webhook is. You don't need to read a single line of this repo. If you can type a sentence, you can run a whale deck.
Every whale you've watched buy a coin at 3am, while you were asleep, reading charts or doing it all by hand: that's the gap. million watches the wallets without blinking. Your coding agent sits on top of it and does the part that used to need a developer: installing it, wiring it up, explaining what it did, changing it when you ask.
you set it up. I have 5 SOL and I want to follow patient whales
agent installs the deck, checks your Helius key, asks three questions,
applies the Swing Copy preset, sizes it to your 5 SOL, starts the feed
you how's it going?
agent Feed healthy, 2 positions open. STONK closed +7% on the
trailing stop. CATE fired a ladder signal but was already bought an
hour ago, so it waited.
you why didn't it buy K7Pa…pump? everyone was talking about it
agent Only one wallet you follow bought it, with 0.4 SOL: under your
1.5 SOL minimum for a copy signal. Lowering it would also let in
every small, noisy buy. Want to change it?
you find me whales from this token: <address>
agent pulls its biggest buyers, analyzes them, flags the four wallets
that are really one operator, and adds the rest for you to pick
you watch it and tell me when it buys
agent OPENED FRIES · 0.2 SOL · copy signal from AgmL…zN51,
a wallet you follow that bought 1.8 SOL of it a second ago(An illustration of the conversation, not a record of trades.)
Start with the commands at the top of this page. The agent reads the project, follows the setup playbook, and asks you for what only you can decide: your Helius key, your size, your style, the wallets to start from. Everything it runs is in the open, in this repo.
What your agent can do with it, following the playbooks in .claude/skills (in Claude Code they are also slash commands):
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
million: common questions
- Is million MCP server safe?
- Yes, by our scan: it is graded A (92/100). Read the million safety report
- How do I install million?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does million need an API key?
- No secret keys are declared. It reads 1 setting from the environment.
- Is million maintained?
- The last commit was 52 days ago (2026-09-14). The latest release is v1.0.0.
- How does million compare with other MCP servers?
- safety score 92/100 (higher than 93% of 48,243 servers); tools 14 (the typical server has 7); tools that change things 14% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.