Ask ChatGPT who bought a coin yesterday and you get a guess. The chatbot has no view of the market. What it knows comes from text it read months ago. It can explain a chart pattern, but it can\u2019t tell you what the price did this\u00a0morning.<\/p>\n
The fix is a plug-in standard called MCP, short for Model Context Protocol. An MCP server is a data source that an AI chatbot can call while it writes its answer. Connect a crypto MCP server to Claude, ChatGPT or Cursor, and \u201cwho bought this coin?\u201d becomes a lookup against real\u00a0trades.<\/p>\n
I checked nine crypto MCP servers against six questions traders ask, using each vendor\u2019s docs. On 6 October 2026 I tested four of them myself: Bitquery, CoinGecko, DexPaprika and altFINS. Then I ran the top pick on one live question: who made money on a Solana token that rose 52% in a\u00a0week?<\/p>\n
Disclosure: This story was written with the assistance of an AI writing program (Claude), which also ran the queries. I checked every number against the raw output. There are no affiliate links.<\/em><\/p>\n Best for on-chain trading analysis (wallets, profit, DEX trades, Hyperliquid futures):<\/strong> BitqueryBest free starting point:<\/strong> CoinGecko, which has a public server that needs no\u00a0keyBest for labelled \u201csmart money\u201d wallets:<\/strong>\u00a0NansenBest for Solana wallet profit:<\/strong>\u00a0BirdeyeBest if you write SQL:<\/strong>\u00a0DuneBest for market data with news and chart analysis:<\/strong> CoinMarketCapBest for ready-made chart signals:<\/strong>\u00a0altFINSBest free DEX pool data:<\/strong> DexPaprikaBest for social sentiment:<\/strong> Santiment<\/p>\n A crypto MCP server is a connector that gives an AI chatbot live market or blockchain data through a list of tools. Ask Claude which Hyperliquid futures markets have the most buyers, and Claude picks a tool from the server\u2019s list, the server runs the query, and Claude reads the rows back to you. Expand the answer and you can see the exact tool\u00a0call.<\/p>\n The AI is only as good as the tool it calls. A server built on exchange price feeds can\u2019t tell you which wallets bought. A server built on blockchain trades can\u2019t tell you what people say about a coin online. So the useful question is which server holds the data your question\u00a0needs.<\/p>\n What is this coin worth?<\/strong> Price, market cap and volume across exchanges.What did a small token do?<\/strong> Price history for a token that trades only on a decentralized exchange (DEX), minute by\u00a0minute.What is moving?<\/strong> Trending tokens and fresh launches.Who is buying, and who made money?<\/strong> Trades and profit for each\u00a0wallet.Where is the borrowed money?<\/strong> Data on perpetual futures, the no-expiry contracts most crypto traders use to trade with borrowed funds. That means funding rates (the hourly fee one side pays the other), open interest (the value of all open contracts) and liquidations (positions closed because the trader\u2019s margin ran\u00a0out).What is the crowd saying?<\/strong> Social sentiment and ready-made chart\u00a0signals.<\/p>\n What each server can answer, from each vendor\u2019s tool list and docs on 6 October 2026. Chart made by the\u00a0author.<\/p>\n The same comparison in text, for phone readers and anyone who can\u2019t see the\u00a0chart:<\/p>\n Bitquery<\/strong> answers 2, 3, 4 and 5; partly 1; not 6. Free 7-day\u00a0trial.CoinGecko<\/strong> answers 1, 2 and 3; partly 4 (paid) and 5; not 6. Free, no\u00a0key.Nansen<\/strong> answers 1, 2, 3 and 4; partly 5 and 6. Trial\u00a0credits.Birdeye<\/strong> answers 1 and 2; partly 3 and 4; not 5 or 6. Free\u00a0key.Dune<\/strong> answers 2 and 4 through SQL; partly 1, 3 and 5; not 6. 14-day\u00a0trial.CoinMarketCap<\/strong> answers 1 and 6; partly 3 and 5; not 2 or 4. Free\u00a0key.altFINS<\/strong> answers 1 and 6; partly 3; not 2, 4 or 5. Free\u00a0key.DexPaprika<\/strong> answers 3; partly 1 and 2; not 4, 5 or 6. Free, no\u00a0key.Santiment<\/strong> answers 1 and 6; partly 3; not 2, 4 or 5. Free\u00a0tier.<\/p>\n \u201cPartly\u201d means a paid tier, a narrower data set, or only some of the question. Everything comes from each server\u2019s own tool list or docs on 6 October\u00a02026.<\/p>\n Best for:<\/strong> who traded, at what price, and with what\u00a0result.<\/p>\n Bitquery reads trades straight from the blockchain. Its server covers DEX trades on Ethereum, Solana, BNB Chain, Base, Arbitrum, Optimism, Polygon, Tron, Robinhood Chain and Arc. It also covers Hyperliquid, a crypto futures exchange with its own blockchain, and Polymarket, a prediction market.<\/p>\n What it answers from its own\u00a0data:<\/p>\n Price candles down to one second for any token, including ones launched an hour\u00a0ago.Trending tokens, new launches, and the first wallets to buy each\u00a0launch.Every trade a wallet made, its open positions, and its profit at average\u00a0cost.Hyperliquid funding, open interest, liquidations and trader positions.Polymarket odds, trades and top wallets, plus address labels and fund\u00a0tracing.<\/p>\n Two answers it gave me on 6 October\u00a02026:<\/p>\n In all 15 of the largest Hyperliquid markets, most accounts were long: 65% on BTC, 73% on ETH and up to 85% on a gold contract. Every long is matched by a short of the same size. So a long-heavy account count means many small longs facing fewer, larger shorts. On BTC, ETH and SOL, funding sat at the exchange\u2019s default rate of about 11% per year, so the crowd of longs paid nothing\u00a0extra.In the 24 hours to 13:30 UTC, BTC had 2,282 liquidations worth $15.5 million, and 70% of them hit longs. On xyz:SPCX, a futures market on SpaceX, 1,634 liquidations worth $9 million hit shorts 81% of the time, while its price rose\u00a08.5%.<\/p>\n Weak spots:<\/strong> the trade and price tools keep about 30 days of history (its own coverage check said 30.6 days). It has no social or news data. It prices coins from on-chain trades and has no exchange order-book data. It has no ready-made indicators: you get candles, and the AI works out RSI or moving averages\u00a0itself.<\/p>\n Setup and price:<\/strong> hosted at https:\/\/mcp.bitquery.io with browser sign-in. A 7-day trial gives 100 credits with no card. Trading MCP costs $19 per month for 32 trading tools; AI Investigation MCP costs $149 per month for every tool (product page<\/a>, setup\u00a0guide<\/a>).<\/p>\n Best for:<\/strong> prices, market caps and DEX pool data with no\u00a0sign-up.<\/p>\n CoinGecko runs a public server at https:\/\/mcp.api.coingecko.com\/mcp that needs no key. The server works differently from the rest: it has two tools, one that searches the CoinGecko API docs and one that runs code against the API. The AI writes a short script for each question.<\/p>\n On the free server I got ORCA\u2019s price ($2.57), market cap ($155.6 million) and 24-hour change (+30%). The server also returned daily candles for ORCA\u2019s main pool, the latest 300 trades with wallet addresses, the trending list and futures data. CoinGecko\u2019s daily ORCA closes matched Bitquery\u2019s within a\u00a0cent.<\/p>\n Weak spots:<\/strong> the \u201ctop traders\u201d call returned \u201cNot found\u201d on the free server. CoinGecko\u2019s docs put top traders and holders on the Analyst plan, $129 per month, capped at 50 wallets per token. A paid key starts at $35 per month (docs<\/a>, pricing<\/a>).<\/p>\n Best for:<\/strong> knowing who owns a wallet as well as what it\u00a0did.<\/p>\n Nansen\u2019s server lists 50 tools: token prices and candles, who bought and sold a token, wallet profit, holders, Hyperliquid positions, prediction markets and technical indicators. Its edge is labels. Nansen tags funds, exchanges and its own \u201csmart money\u201d list, and those names come back with the\u00a0data.<\/p>\n Weak spots:<\/strong> no funding rates or open interest in the tool list, and no social data. Calls cost credits: the free tier gives 100 trial credits and then tops up to 10 per day, while one profit leaderboard call costs 150. Pro costs $69 per month (tool list<\/a>, credits<\/a>).<\/p>\n Best for:<\/strong> Solana traders who want top traders and wallet profit per\u00a0token.<\/p>\n Birdeye covers prices, candles, token trades, holders and top traders on many chains, plus wallet profit on Solana. Birdeye\u2019s docs call the server keyless, but my keyless call came back \u201cUnauthorized\u201d, so plan on a free API\u00a0key.<\/p>\n Weak spots:<\/strong> wallet profit is Solana only, and the free tier allows one request per second. Lite costs $39 per month\u00a0(docs<\/a>).<\/p>\n Best for:<\/strong> custom questions no ready-made tool\u00a0answers.<\/p>\n Dune\u2019s server gives the AI SQL access to Dune\u2019s tables across more than 100 chains, plus its community dashboards. Anything a table holds, the AI can query: top wallets, flows, or a protocol\u2019s fees.<\/p>\n Weak spots:<\/strong> the answer is only as good as the SQL the AI writes, and every run costs credits. The free plan has no API access after a 14-day trial; Analyst costs $75 per month\u00a0(docs<\/a>).<\/p>\n Best for:<\/strong> one place for quotes, chart analysis, news and market narratives.<\/p>\n CoinMarketCap\u2019s server has 12 tools covering quotes, technical analysis, on-chain and futures metrics, narratives and news. A free Basic key works, and a pay-per-call route charges 0.01 USDC per request with no key\u00a0(docs<\/a>).<\/p>\n Weak spots:<\/strong> market-wide numbers only, with no wallet-level data.<\/p>\n Best for:<\/strong> traders who want indicators and chart patterns without doing the maths themselves.<\/p>\n altFINS covers more than 150 indicators and 130 signal types, plus 35 candle patterns, across more than 2,000 assets. On my test, altFINS flagged ORCA as overbought on 5 October, with RSI above 70 and Stochastic above 80, and listed it as an unusual-volume gainer. The free Basic plan includes MCP access\u00a0(docs<\/a>).<\/p>\n Weak spots:<\/strong> chart analysis only, with no wallet data. altFINS put ORCA\u2019s market cap at $69 million, while CoinGecko and Bitquery both showed about $155 million. Check market caps against a second\u00a0source.<\/p>\n Best for:<\/strong> pools, liquidity and token details across 36 chains,\u00a0free.<\/p>\n DexPaprika\u2019s server at https:\/\/mcp.dexpaprika.com\/streamable-http needed no key on my test and returned ORCA’s details and its pools. Token candles asked for a paid key (Dev, $30 per month), and the server pointed me to free pool candles instead (pricing<\/a>).<\/p>\n Weak spots:<\/strong> no wallet tools, so it can\u2019t say who\u00a0bought.<\/p>\n Best for:<\/strong> what the crowd is saying, next to price and on-chain\u00a0metrics.<\/p>\n Santiment\u2019s seven tools cover price, market cap, social volume and sentiment, trending stories and analyst insights, with metrics such as exchange inflows and daily active addresses. The free tier allows 500 calls per day\u00a0(guide<\/a>).<\/p>\n Weak spots:<\/strong> time series only, with no wallet-level data.<\/p>\n Also worth knowing:<\/strong> CryptoQuant (exchange flows and miner data), Arkham (entity labels and counterparties), Glassnode (on-chain metrics, with 30 days of history free and no key) and Token Terminal (protocol fees and revenue). Alchemy\u2019s server gives raw node data and no trading data. Moralis\u2019s MCP package has had no update since September 2025. Messari, now owned by Blockworks, sells its server only through its sales\u00a0team.<\/p>\n ORCA, the token of the Solana exchange Orca, rose 52% in the seven days to 6 October, from $1.67 to $2.54. Trading ran at about $1 million per day from 30 September to 3 October, then jumped to $6.1 million on 4 October and $10.3 million on 5 October. I asked Claude, with Bitquery connected, who made money on the\u00a0move.<\/p>\n Step 1: find the token.<\/strong> Claude found ORCA in a trending_tokens screen of the week’s gainers. The screen returns the token’s address as well as its ticker. That matters, because anyone can create a coin called\u00a0ORCA.<\/p>\n Step 2: screen the wallets.<\/strong> profitable_traders_by_token ranked every wallet that traded ORCA that week. The top\u00a0three:<\/p>\n Wallet Ffz3\u2026Z47h bought $3.13 million of ORCA in 161 trades over 29 hours and sold nothing. Estimated gain: $719,012.Wallet FkaL\u20263MZp made 9,790 trades, buying $3.54 million and selling $2.82 million. Estimated gain: $112,852.Wallet 7xD1\u2026aLrV bought $168,014 and sold nothing. Estimated gain:\u00a0$52,320.<\/p>\n Step 3: check the profit properly.<\/strong> The screen estimates profit as sales minus purchases, plus the value of what the wallet still holds. trader_positions works it out again at average cost and splits cash already taken from gains on\u00a0paper.<\/p>\n Wallet 1 paid an average of $2.07 per ORCA. At $2.55, its 1.51 million tokens were worth $3.86 million. Its $725,376 gain was all on\u00a0paper.Wallet 3 looked the same: a $52,684 gain on paper, nothing\u00a0sold.Wallet 2 was the only one to take profit: about $100,000 realized, a 3.7% return on what it sold, plus about $20,000 on paper at that hour\u2019s price. It held each position for about seven hours on\u00a0average.<\/p>\n Step 4: read the trades.<\/strong> trader_trades lists every swap with its transaction hash. Wallet 1’s five largest buys were each exactly $25,000 in USDC, routed through Jupiter. In one of them, at 19:02 UTC on 4 October, the other side of the trade was wallet 2 (transaction on Solscan<\/a>).<\/p>\n So wallet 2 fills other people\u2019s orders. It acts as a market maker, a trader that quotes both buy and sell prices and earns the gap. Copying it would teach you\u00a0nothing.<\/p>\n Wallet 1\u2019s buys made up 19% of all ORCA trading on 4 and 5 October, the two days the price climbed from $1.80 to $2.42. Bitquery\u2019s label lookup had no name for the wallet. Its largest buys came in identical $25,000 blocks, which looks like a fund or a treasury desk working a large order. Nothing on-chain proves who owns\u00a0it.<\/p>\n The lesson: a \u201cmost profitable traders\u201d list is mostly paper gains and market makers. Ask the AI two follow-ups every time. Is that profit realized or on paper? Is this wallet a market\u00a0maker?<\/p>\n Hosted servers take about two\u00a0minutes:<\/p>\n Claude (web or desktop):<\/strong> Settings \u2192 Connectors \u2192 Add custom connector. Paste the server URL (for Bitquery, https:\/\/mcp.bitquery.io) and sign in when the browser\u00a0asks.ChatGPT:<\/strong> Settings \u2192 Connectors \u2192 add a custom connector with the same URL. Bitquery\u2019s guide lists Plus, Pro or Business as the plans that allow\u00a0it.Claude Code:<\/strong> run claude mcp add –transport http bitquery https:\/\/mcp.bitquery.io in a terminal.Cursor:<\/strong> Settings \u2192 MCP \u2192 Add new MCP server, then paste the\u00a0URL.<\/p>\n Servers that ask for an API key take it in the connector settings or a header. Servers you install yourself with npm or pip go in the client\u2019s config file, and each project\u2019s README has the exact\u00a0block.<\/p>\n Connect only the servers a chat needs. Each one adds its tool list to the conversation, and the AI picks tools by reading their descriptions. Two servers with similar tools make it\u00a0guess.<\/p>\n \u201cWhich tokens on Base gained the most this week? Skip anything under $5 million in volume and flag names that look\u00a0fake.\u201d\u201cWho made the most money on [token address] this week? Check the top five at average cost and tell me which gains are realized.\u201d\u201cWho were the first 20 buyers of [token address] after launch, and how many still hold\u00a0it?\u201d\u201cWhich Hyperliquid markets have the highest share of accounts long, and what does funding cost them per\u00a0year?\u201d\u201cShow the last 24 hours of Hyperliquid liquidations by market. Were they mostly longs or\u00a0shorts?\u201d\u201cWho are the top 10 wallets in this Polymarket market, and do any carry exchange\u00a0labels?\u201d<\/p>\n Paper gains reported as profit.<\/strong> The ORCA walkthrough shows the pattern. Ask whether a gain is realized every time a number looks\u00a0big.<\/p>\n Junk at the top of every screen.<\/strong> When I sorted Base tokens by weekly gain, the first row claimed a rise of more than 100 million percent, caused by one stray swap. Another showed a fake \u201cUSD\u201d coin, with an odd character in its name, valued at $4.6 trillion. Set a minimum volume, and check the contract address before you trust a\u00a0ticker.<\/p>\n Two numbers for one thing.<\/strong> CoinGecko listed Hyperliquid\u2019s BTC open interest at $3.45 billion. Bitquery said $1.74 billion, and its docs say it counts one side of the book. CoinGecko\u2019s figure is about twice that, which fits counting both sides. Ask what a number measures before you compare\u00a0servers.<\/p>\n A wallet is not a person.<\/strong> Market makers and exchange accounts show up as \u201ctraders\u201d. A bot can sign trades from one address while its tokens sit in\u00a0another.<\/p>\n Old data.<\/strong> Ask for the time of the newest row in every answer. Bitquery\u2019s lag was zero minutes when I checked, but no server promises\u00a0that.<\/p>\n Text written by strangers.<\/strong> Token names and memos are written by whoever created them, and the AI reads them as part of its input. A token name can carry instructions. Keep servers that can move money, such as an exchange account with trading keys, out of the same chat as your data\u00a0servers.<\/p>\n It is not advice.<\/strong> These tools tell you what already happened, quickly. They do not tell you what happens\u00a0next.<\/p>\n Binance and CCXT both ship servers that can read your account and place trades. Binance\u2019s runs in a separate sub-account with no outside withdrawals. CCXT\u2019s runs on your own machine across more than 100 exchanges, and trading is opt-in (CCXT docs<\/a>). Both are execution tools, so they sit outside this comparison. Start read-only, and give an AI trading keys only after you trust its analysis.<\/p>\n What is the best MCP server for crypto\u00a0trading?<\/strong><\/p>\n For on-chain trading analysis, my pick is Bitquery MCP: it covers DEX trades, wallet profit and Hyperliquid futures, including funding and liquidations. Nansen is the closest rival if named wallets matter more to you. For free market-wide prices, start with CoinGecko\u2019s public\u00a0server.<\/p>\n Can ChatGPT or Claude analyse crypto\u00a0trades?<\/strong><\/p>\n Yes, once you connect an MCP server. On their own they have no live prices, so treat any number they give without a tool call as a\u00a0guess.<\/p>\n Is there a free crypto MCP\u00a0server?<\/strong><\/p>\n Yes. CoinGecko (https:\/\/mcp.api.coingecko.com\/mcp) and DexPaprika both answered my calls without a key. altFINS and Santiment have free tiers, and Bitquery has a 7-day\u00a0trial.<\/p>\n Can an AI trade crypto for\u00a0me?<\/strong><\/p>\n It can, through exchange servers such as Binance\u2019s or CCXT\u2019s. Keep those separate from your data servers, and test with read-only access\u00a0first.<\/p>\n How far back does crypto MCP data\u00a0go?<\/strong><\/p>\n It depends on the server. Bitquery\u2019s trade tools keep about 30 days, Glassnode\u2019s free access covers 30 days, and Dune\u2019s SQL reaches the full history of its\u00a0tables.<\/p>\n The Best MCP Servers for Crypto Trading Analysis in 2026<\/a> was originally published in Coinmonks<\/a> on Medium, where people are continuing the conversation by highlighting and responding to this story.<\/p>","protected":false},"excerpt":{"rendered":" Claude and ChatGPT can\u2019t see live crypto markets on their own. I compared nine MCP servers that fix that, tested four, and ran the top pick on a real\u00a0trade. Ask ChatGPT who bought a coin yesterday and you get a guess. The chatbot has no view of the market. What it knows comes from text […]<\/p>\n","protected":false},"author":0,"featured_media":236323,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[2],"tags":[],"class_list":["post-236322","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-interesting"],"_links":{"self":[{"href":"https:\/\/mycryptomania.com\/index.php?rest_route=\/wp\/v2\/posts\/236322"}],"collection":[{"href":"https:\/\/mycryptomania.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/mycryptomania.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"replies":[{"embeddable":true,"href":"https:\/\/mycryptomania.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=236322"}],"version-history":[{"count":0,"href":"https:\/\/mycryptomania.com\/index.php?rest_route=\/wp\/v2\/posts\/236322\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/mycryptomania.com\/index.php?rest_route=\/wp\/v2\/media\/236323"}],"wp:attachment":[{"href":"https:\/\/mycryptomania.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=236322"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/mycryptomania.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=236322"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/mycryptomania.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=236322"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}Quick answer: the best crypto MCP servers in October\u00a02026<\/h4>\n
What is a crypto MCP\u00a0server?<\/h4>\n
How I compared them: six trader questions<\/h4>\n
1. Bitquery MCP: best for on-chain trading\u00a0analysis<\/h4>\n
2. CoinGecko MCP: best free starting\u00a0point<\/h4>\n
3. Nansen MCP: best for labelled \u201csmart\u00a0money\u201d<\/h4>\n
4. Birdeye MCP: best for Solana wallet\u00a0profit<\/h4>\n
5. Dune MCP: best if you write\u00a0SQL<\/h4>\n
6. CoinMarketCap MCP: best for market data with\u00a0news<\/h4>\n
7. altFINS MCP: best for ready-made chart\u00a0signals<\/h4>\n
8. DexPaprika MCP: best free DEX pool\u00a0data<\/h4>\n
9. Santiment MCP: best for social sentiment<\/h4>\n
Walkthrough: who made money on ORCA this\u00a0week?<\/h4>\n
How do you connect a crypto MCP server to Claude or\u00a0ChatGPT?<\/h4>\n
Prompts worth\u00a0copying<\/h4>\n
Where AI trading analysis goes\u00a0wrong<\/h4>\n
What about exchange MCP\u00a0servers?<\/h4>\n
FAQ<\/h4>\n