Bitpoort
On-chain blockchain data for AI agents.
What it can do
- Query Blocks: Get recent blocks for a specific blockchain. Returns block number, hash, timestamp, tx count, and gas used.
- Query Transactions: Get transactions for a chain, optionally filtered by block number. Returns tx hash, from/to addresses, USD value, type, and method name.
- Search Rag: Semantic search over indexed blockchain data. Returns ranked results with text, topic, chain, and relevance score. Uses hybrid dense+BM25 retrieval.
What data it sees
Do you need an account
No: the server works without sign-in
On-chain blockchain data for AI agents. 41 MCP tools for whale tracking, entity analysis, exchange flows, ML predictions, wallet profiling, direct Ethereum RPC, and cross-chain signals across Ethereum, Bitcoin, and Hyperliquid.
How to connect
How to connect Bitpoort to Claude
The server address to paste into Claude settings:
https://on-chain-data--bitpoort.run.tools
- Open Claude (claude.ai or the desktop app).
- Go to Settings → Connectors.
- Click Add custom connector.
- Paste the server address copied below into Remote MCP server URL and click Add.
- In a chat, click + → Connectors and switch the new connector on.
Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.
Authorization
After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.
How to connect Bitpoort to ChatGPT
The server address to paste into ChatGPT settings:
https://on-chain-data--bitpoort.run.tools
- Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
- Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
- Open Settings → Connectors and click Create.
- Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
- Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
- In a new chat open + → Apps/Connectors and enable the connector.
OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.
Authorization
On first use ChatGPT opens the service's sign-in window. Sign in and approve access.
How to connect Bitpoort to Cursor
The server address to paste into Cursor settings:
https://on-chain-data--bitpoort.run.tools
Fastest: click Open in Cursor below and confirm the prompt.
Manually:
- In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
- Paste the JSON copied below into
~/.cursor/mcp.json(per project:.cursor/mcp.jsonin the repo root). - Save the file. The server appears in the MCP list; authorize it there if asked.
Authorization
If the service needs sign-in, an authorize button appears next to the server in the MCP list.
Server tool list (41)
Raw names from tools/list. Only developers need these.
| query_blocks | Get recent blocks for a specific blockchain. Returns block number, hash, timestamp, tx count, and gas used. |
| query_transactions | Get transactions for a chain, optionally filtered by block number. Returns tx hash, from/to addresses, USD value, type, and method name. |
| search_rag | Semantic search over indexed blockchain data. Returns ranked results with text, topic, chain, and relevance score. Uses hybrid dense+BM25 retrieval. |
| get_whale_activity | Get recent whale (high-value) transactions. Returns structured array with tx_hash, from/to addresses and labels, value_usd, tier (MID/LARGE/MEGA), and description. |
| get_intent_detections | Get detected behavioral patterns (accumulation, distribution, arbitrage, rug signals, etc.). Includes confidence scores and risk levels. |
| get_pipeline_status | Get the current state of the 7-stage data pipeline (INGEST -> NORMALIZE -> ENRICH -> CHUNK -> EMBED -> INDEX -> STORE). Shows throughput, latency, queue depth, and error counts per stage. |
| get_chain_status | Get processing status for a specific blockchain including block watermarks, lag, and errors per pipeline stage. |
| get_health | Get the overall system health score (0-100) and status (HEALTHY/DEGRADED/IMPAIRED/CRITICAL) with per-stage breakdown. |
| inspect_block | Get full detail for a specific block including all transactions, whale activity, and RAG chunks. Useful for deep investigation. |
| get_logs | Get recent system log entries, optionally filtered by level (INFO/WARNING/ERROR) and service (ingest/normalize/enrich/chunk/embed/index/store/scheduler). |
| get_alerts | Get alert history including triggered rules, severity, and resolution status. |
| get_stats | Get aggregate system statistics: total blocks, transactions, RAG chunks, whale transactions, active intents, DLQ entries, and per-chain breakdowns. |
| ask_blockchain | Ask a natural language question about blockchain activity. Returns an array of relevant data chunks with text, topic, chain, and relevance score. Best for: 'What happened on ETH today?', 'Any whale movements?', 'What has Binance been doing?'. |
| get_network_summary | Get a structured network summary: hourly stats (tx_count, volume, gas), whale activity (count, top movements), latest block, and system health. Use for fast orientation. |
| get_entity_activity | Get activity history for a named entity (e.g. 'Binance', 'Wintermute') or wallet address. Returns structured periods with tx_count, total_value_usd, net_flow_usd, and tx_types breakdown. |
| get_mev_leaderboard | Get MEV bot leaderboard ranked by 7-day extracted value. Returns bot address, strategy (flash_loan_arb, lending_arb, dex_arb), success rate, total P&L, extracted value, gas costs, and trade count. Use to identify top MEV searchers and arbitrage bots. |
| get_smart_wallets | Get top wallets ranked by 7-day trading performance. Returns wallet address, composite score (0-100), win rate, total P&L, profit factor, protocols used, and trade count. Use to identify smart money, profitable traders, and MEV bots. |
| get_trade_signals | Get composite trade signals from cross-signal analysis. Returns structured signals array with token, direction (bullish/bearish), score (0-100), thesis, and evidence. Also returns activity anomalies vs 7-day baseline. |
| get_predictions | Get ML-based short-term price predictions for tracked tokens. Uses LightGBM trained on 30+ on-chain and technical features with walk-forward validation. Returns per-symbol direction (bullish/bearish), probability, and confidence (high/medium/low). Available horizons: 5m, 10m, 15m. |
| get_conviction_signals | Get conviction signals from cross-signal correlation. Combines 7 sources (swap pressure, smart money, exchange flow, token momentum, risk warnings, smart wallet consensus, MEV bot interest) into a single conviction score (0-100). Returns signals array with token, direction, conviction_score, signal_count, thesis, and evidence. |
| get_exchange_flows | Get exchange inflow/outflow data. Returns aggregate net flow with direction, per-exchange breakdown (inflow/outflow/net per exchange), and per-token flows. Excludes exchange-to-exchange transfers. |
| get_token_flows | Get tokens ranked by net buying or selling pressure. Returns sellers[] and buyers[] arrays with token, buy_usd, sell_usd, net_usd, buy_ratio, and swap_count. Based on DEX swap data, excludes stablecoins. |
| get_price_history | Get recent price candles (OHLCV) and price change for a token. Returns candles[] array with OHLCV data and price_change object with current/past price and change_pct. Supports 20 major tokens, 1-minute resolution. |
| get_risk_briefing | Get a security-focused risk briefing. Returns structured arrays: risk_events (anomalies), intents (behavioral patterns with confidence/risk_level), and transactions (with risk_score and flags). |
| get_alarm_feed | Get the alarm feed with triggered on-chain events. Returns structured events array with alarm_type, severity, chain, timestamp, title, detail, and value_usd. |
| get_alarm_categories | List all available alarm categories with severity levels, supported chains, and default thresholds. |
| get_emerging_tokens | Get emerging tokens ranked by momentum score. Returns tokens discovered on-chain with swap activity, unique traders, holder growth, and smart money interest. Higher score = stronger momentum signal. Use for early token discovery and alpha. |
| get_trending_tokens | Get tokens ranked by swap volume over a time window. Returns symbol, volume, change percentage, swap count, unique wallets, and buy/sell ratio. Use to identify market momentum and active tokens. |
| get_wallet_profile | Get complete wallet profile for an Ethereum address: label, classification, risk score, volume, transaction count, top tokens, top counterparties, and cluster membership. Use for investigating any address. |
| get_intelligence_feed | Unified event feed from 6 sources: whale transfers, intent detections, liquidation risks, profitable trades, MEV extractions, and signals. Chronological stream of what is happening on-chain. Filter by event_type for specific categories. |
| get_hl_market | Hyperliquid market state: smart money positioning (long/short %), aggressive flow direction, and funding rates with open interest for all coins. Single call for full HL market overview. |
| get_hl_traders | Top Hyperliquid perpetual traders ranked by smart money score. Returns win rate, PnL, Sharpe ratio, profit factor, edge score, and best coin. Use to identify skilled perp traders. |
| get_btc_flows | Bitcoin whale flows with entity enrichment from 2.3M labeled addresses. Returns flow type, BTC/USD amount, from/to entity names, intent classification, and market signal. Uses CIOH clustering for entity resolution. |
| get_cross_chain_signals | ETH on-chain to Hyperliquid perpetual correlation signals. Detects when ETH whale activity (accumulation, exchange withdrawal) correlates with HL positioning changes. Returns signal type, entities, values, confidence, direction, and time lag. |
| rpc_get_balance | Get ETH balance of an Ethereum address. Returns balance in ETH and wei, with entity label if known. Use for checking wallet balances, exchange holdings, or contract balances. |
| rpc_get_block | Get Ethereum block details: timestamp, gas usage, transaction count, base fee. Omit block_number for latest block. Set include_transactions=true for transaction list with from/to labels and ETH values. |
| rpc_get_transaction | Get full transaction details by hash: from/to with entity labels, value in ETH, gas cost, status (success/reverted), log count. Combines tx data and receipt in one call. |
| rpc_get_logs | Get event logs emitted by a contract. Useful for tracking Transfer events, approvals, swaps, etc. Max 2000-block range. Default: last 1000 blocks. Transfer event topic: 0xddf252ad1be2c89b69c2b068fc378daa952ba7f163c4a11628f55a4df523b3ef |
| rpc_get_contract_info | Check if an address is a smart contract, get its ETH balance, code size, and transaction count (nonce). Also returns entity label and classification if known. Single call to classify any Ethereum address. |
| rpc_read_contract | Read smart contract state by calling a view function. Supports common ERC-20 functions: name(), symbol(), decimals(), totalSupply(), balanceOf(address), owner(). Pass function signature and arguments. No ABI file needed. |
| rpc_trace_transaction | Get internal call trace of a transaction: all internal calls, ETH transfers, contract interactions with entity labels. Shows the full execution tree. Useful for understanding complex DeFi transactions. |