EMC2 AI MCP server

• Registry nameio.emc2ai/einsteinverified in the MCP registry

The registry name sits under emc2ai.io. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

• Stateanswerschecked 2026-10-26
• Tools40
• Server calls itselfAgentEinstein
• Server version3.4.0
• Protocol version2025-06-18

On 2026-10-26 the server answered initialize and tools/list without a sign-in. First answer in 243 ms.

• Its tools do every use case we checked: track whale wallets and smart money flows; check token contracts for security risks; forecast crypto prices with two time-series models.
• Checked on 2 of the 7 days it takes to judge reliability.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

• INITE MCP scoreafter a weeka score needs 7 daily checks: 2 so far
• What an agent can do with it3 of 3 use cases
• Answeredmeasuring2 of the 7 daily checks it takes to print a share
• Median first answer372 ms
• Space in an agent's context≈ 7,209 tokensthe definitions of all its tools (40), which an agent carries on every turn
• Tool definitionsA · 100 of 100
• Typed results40 of 40 toolsdeclared outputSchema: results come typed, read once

• Every tool passes all six checks.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

• get_price_forecast

  Einstein's dual-model machine-learning price forecast (Google TimesFM 3.0 + Kronos) for BTC, ETH, SOL or BNB, including whether the two models agree and the direction/drift each projects. Pre-computed every 4 hours; returns the cached run…

• get_forecast_accuracy

  The measured, out-of-sample accuracy of Einstein's own price forecasts — MAPE and direction hit-rate per model, asset and horizon, scored after each forecast's horizon elapsed. Hit rates are computed over INDEPENDENT trials (one forecast…

• get_market_sentiment

  Multi-source market sentiment in one read: the crypto Fear & Greed index, CoinMarketCap’s variant, the traditional-market (CNN) Fear & Greed, and the Altcoin Season index. Useful for framing any "how is the market feeling" question.

• get_top_movers

  The largest 24h movers across the major-cap crypto universe, gainers or losers, from a refreshed market snapshot.

• get_smart_money_flow

  Where profitable on-chain wallets have been rotating capital recently, from the tracked smart-money cohort.

• get_hyperliquid_whales

  Consensus positioning of the largest Hyperliquid perp traders plus current funding rates — i.e. what big leveraged money is actually long or short, and what it costs to hold that side. A coin held by fewer than 3 of the read whales is…

• get_robinhood_whale_prints

  Individual large DEX trades on Robinhood Chain (EVM 4663) — the tokenized equities (NVDA, SPY, HIMS) and Pons memecoin flow that no mainnet whale feed carries, each with its token, side, venue and USD value. Every print is valued through…

• get_polymarket_whales

  Large and unusually-early positions taken on Polymarket prediction markets, surfaced from the insider-detection scan.

• get_prediction_market_catalysts

  Upcoming dated events on Polymarket whose odds are moving — the catalysts most likely to move crypto or macro narratives next.

• get_bitcoin_cycle_position

  Where Bitcoin sits in its cycle by on-chain measures — realized-profit, holder-behaviour and valuation indicators rather than price alone.

• check_token_safety

  Free honeypot / risk screen for an EVM token contract, from the cached GoPlus security dataset. This is the quick screen — the paid analyze_token_security tool runs a live, deeper scan on any contract including ones not in the cache.

• get_congress_trades

  Recently disclosed stock and asset transactions by members of the US Congress, newest first.

• get_government_contracts

  Recent notable US federal contract awards — useful for tracking which public companies are winning government money.

• get_analyst_accuracy

  Scored track record of public crypto commentators and influencers whose calls Einstein has graded against what actually happened. Ranked by measured hit-rate, not follower count. Reports how many calls are graded versus still awaiting…

• get_smart_money_inflow

  Tokens ranked by NET smart-money inflow in US dollars over the last 24 hours, from wallets Binance tracks as consistently profitable. Reports the number of distinct wallets behind each figure — a large inflow from one wallet is a…

• get_social_hype

  Tokens ranked by social buzz over the last 24 hours, each with a sentiment classification (Positive/Negative/Neutral), the number of distinct KOL accounts discussing it, and a one-line summary of what is actually being said. BSC. Use when…

• get_launchpad_radar

  Tokens that just migrated off a bonding curve onto a DEX, with holder-distribution forensics: what share the dev, snipers, insiders and bundler wallets hold, plus wash-trading tags. Covers Pump.fun, Bonk, Raydium, Meteora, Four.meme, Flap…

• list_einstein_capabilities

  Everything Einstein can do through this connector, split into free tools and paid tools with their prices, plus how billing works. Call this when you are not sure which tool fits, or before telling a user something isn't available.

• ask_einstein

  Open-ended crypto and DeFi analysis from Einstein's full research stack — use this when no more specific tool fits, or when the question spans several domains. Returns a written analysis grounded in live on-chain and market data. [Paid…

• scan_v4_hooks

  Census the Uniswap v4 hook layer on Robinhood Chain (4663), BNB Chain (56), Ethereum (1) and Base (8453): which hook contracts are creating the most pools, what each is permitted to do to a trader or an LP (take an arbitrary cut of a…

• forecast_chart

  Real-time data retrieval and compute for any token, on any supported chain — bundles a live dual-model price forecast (Google TimesFM 3.0 + Kronos, with quantile confidence bands) at no separate charge. Unlike the free get_price_forecast…

• analyze_token_security

  Live security analysis of a token contract: rug-pull risk, holder concentration, sniper activity, dangerous approvals, or a full smart-contract audit. Choose the analysis with `kind`. [Paid: $0.35–$2.00 per call from your Einstein credit…

• inspect_onchain

  Block-explorer intelligence on 18 EVM chains, from live Etherscan V2 data. `contract` reviews a deployed contract — resolving proxies FIRST (EIP-1967, the legacy OpenZeppelin slot USDC still uses, EIP-1167 clones, Gnosis Safe, EIP-2535…

• analyze_wallet

  Analyze any wallet address: current holdings, realized/unrealized P&L, a trust score, forgotten or dust assets, unclaimed airdrops, or quantum-resistance of its address type. [Paid: $0.25–$1.00 per call from your Einstein credit balance…

• analyze_tokenized_stocks

  The market where memecoins are priced in SHARES, on Base and Robinhood Chain. Float-corner risk (whose on-chain stock float is locked in one pool while the issuer cannot mint), stock-paired launches with their tax and dividend structure…

• track_whales

  Live intelligence on large capital: on-chain whale transfers and accumulation, Hyperliquid perp whale positioning, or the profitable smart-money cohort. [Paid: $0.45–$0.50 per call from your Einstein credit balance. Free alternatives…

• scan_market

  Live market scans: top gainers, biggest movers, alpha-ranked gainers with quality filters, the altcoin-season reading, technical analysis for one asset, or the current market-regime classification. [Paid: $0.25–$0.60 per call from your…

• detect_mev

  Detect sandwich attacks and MEV extraction against a token or wallet, or get a protected routing recommendation for a pending transaction. [Paid: $0.50–$0.60 per call from your Einstein credit balance. Free alternatives exist for several…

• find_arbitrage

  Scan for live arbitrage: DEX price dislocations, flash-loan-fundable routes, cross-chain spreads, or prediction-market mispricings. [Paid: $1.00 per call from your Einstein credit balance. Free alternatives exist for several of these…

• scan_launchpads

  New and trending token launches: Pump.fun (Solana), Zora (Base), or the Robinhood Chain market catalog. [Paid: $0.25–$0.40 per call from your Einstein credit balance. Free alternatives exist for several of these — see…

• analyze_bitcoin

  Bitcoin-native analysis: mempool and fee intelligence, network and mining health, BRC-20 tokens, Runes, bridge comparison, or Babylon staking. [Paid: $0.25–$0.85 per call from your Einstein credit balance. Free alternatives exist for…

• assess_quantum_risk

  Assess exposure to cryptographically-relevant quantum computing: organizational PQC readiness, a migration plan, or the quantum risk of a wallet’s address types. [Paid: $0.50–$0.75 per call from your Einstein credit balance. Free…

• generate_quantum_key

  Generate key material from quantum randomness (ANU QRNG): entropy for a BIP-39 wallet seed phrase, an AES-256 encryption key or a signing key, or raw quantum random numbers. The entropy is returned once in the result and is not stored. It…

• analyze_prediction_markets

  Polymarket analysis: browse live markets, scan for insider-shaped positions, measure bid/ask spreads, find high-conviction positioning, or fade over-priced long shots. [Paid: $0.50–$1.50 per call from your Einstein credit balance. Free…

• find_yield

  Find yield: DeFi lending and LP opportunities ranked by risk-adjusted return, Pendle fixed-yield and YT/PT trades, a broad vault discovery sweep, or liquidation opportunities. [Paid: $0.10–$0.75 per call from your Einstein credit balance…

• run_backtest

  Backtest a trading strategy on real historical data: describe rules in plain language for a custom event-driven backtest, run a standard strategy template, or optimize a strategy’s parameters. [Paid: $0.75–$2.00 per call from your…

• get_trade_signals

  Einstein's current live trade signals — the setups its own autonomous engine is acting on, with entry, stop and target levels and the reasoning behind each. [Paid: $0.50 per call from your Einstein credit balance. Free alternatives exist…

• check_content_integrity

  AI moderation of text you supply: a 0-10 quality score with a written rationale and a recommendation, or the list of yield vaults Einstein has scanned. [Paid: $0.05–$0.10 per call from your Einstein credit balance. Free alternatives exist…

• analyze_youtube_video

  Analyse one YouTube video from its link: a summary, timestamped key points, every explicit market call (ticker, direction, conviction, horizon, quote, timestamp) with the current spot price, sponsor mentions, and the channel's graded…

• get_agent_context

  Einstein's own current market context and operating state — the same situational briefing its autonomous engine reads before making a decision. [Paid: $1.00 per call from your Einstein credit balance. Free alternatives exist for several…