Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Agent Einstein — Crypto & Market Intelligence

REMOTE · EMC2AI.IO

AI price forecasts, whale flows, market sentiment and prediction signals. 18 tools free, no account.

Available components

0 this week 78 Trust /100

Last scanned (20 hours ago)

Scores higher than 76% of remote servers

Reachable. Last reached 4 Nov 2026.

Category Crypto and Web3

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security80
Transport & Reachability0
Schema Quality & AI Usability84
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 5033 tokens (~109/item across 46 items; 40 tools + 6 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management93
  • Stability check failed: schema churn in the 30 days we've observed: 3 tool removals, 0 breaking changes, 0 auth/transport breaks, 1 additions. See how to fix → Fail
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 40 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 42 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
  • Supports UI / widget rendering.Pass
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 4 Nov 26 0
    • Resource “Market sentiment gauges” now points somewhere else: ui://einstein/sentiment → ui://einstein/sentiment+mcp security
    • Resource “Price forecast card” now points somewhere else: ui://einstein/forecast → ui://einstein/forecast+mcp security
    • Resource “Top movers table” now points somewhere else: ui://einstein/movers → ui://einstein/movers+mcp security
  • 3 Nov 26 0
    • Resource “Market sentiment gauges” now points somewhere else: ui://einstein/sentiment → ui://einstein/sentiment+mcp security
    • Resource “Price forecast card” now points somewhere else: ui://einstein/forecast → ui://einstein/forecast+mcp security
    • Resource “Top movers table” now points somewhere else: ui://einstein/movers → ui://einstein/movers+mcp security
  • 2 Nov 26 0
    • Resource “Market sentiment gauges” now points somewhere else: ui://einstein/sentiment → ui://einstein/sentiment+mcp security
    • Resource “Price forecast card” now points somewhere else: ui://einstein/forecast → ui://einstein/forecast+mcp security
    • Resource “Top movers table” now points somewhere else: ui://einstein/movers → ui://einstein/movers+mcp security
  • 1 Nov 26 0
    • Resource “Market sentiment gauges” now points somewhere else: ui://einstein/sentiment → ui://einstein/sentiment+mcp security
    • Resource “Price forecast card” now points somewhere else: ui://einstein/forecast → ui://einstein/forecast+mcp security
    • Resource “Top movers table” now points somewhere else: ui://einstein/movers → ui://einstein/movers+mcp security
  • 31 Oct 26 0
    • Resource “Market sentiment gauges” now points somewhere else: ui://einstein/sentiment → ui://einstein/sentiment+mcp security
    • Resource “Price forecast card” now points somewhere else: ui://einstein/forecast → ui://einstein/forecast+mcp security
    • Resource “Top movers table” now points somewhere else: ui://einstein/movers → ui://einstein/movers+mcp security
  • 30 Oct 26 0
    • Resource “Market sentiment gauges” now points somewhere else: ui://einstein/sentiment → ui://einstein/sentiment+mcp security
    • Resource “Price forecast card” now points somewhere else: ui://einstein/forecast → ui://einstein/forecast+mcp security
    • Resource “Top movers table” now points somewhere else: ui://einstein/movers → ui://einstein/movers+mcp security
  • 29 Oct 26 0
    • Resource “Market sentiment gauges” now points somewhere else: ui://einstein/sentiment → ui://einstein/sentiment+mcp security
    • Resource “Price forecast card” now points somewhere else: ui://einstein/forecast → ui://einstein/forecast+mcp security
    • Resource “Top movers table” now points somewhere else: ui://einstein/movers → ui://einstein/movers+mcp security
  • 28 Oct 26 0
    • Resource “Market sentiment gauges” now points somewhere else: ui://einstein/sentiment → ui://einstein/sentiment+mcp security
    • Resource “Price forecast card” now points somewhere else: ui://einstein/forecast → ui://einstein/forecast+mcp security
    • Resource “Top movers table” now points somewhere else: ui://einstein/movers → ui://einstein/movers+mcp security
    • Tool “get_robinhood_whale_prints” rewrote its description, which is the text the model reads security
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 4 Nov 2026 · Probed https://emc2ai.io/api/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=emc2ai.io CN=WE1,O=Google Trust Services,C=US 27 Sept 2026 26 Dec 2026 ECDSA 256 ECDSA-SHA256 860c1da78fbf577c0eaca354011902f1
SANs: emc2ai.io, *.emc2ai.io
CN=WE1,O=Google Trust Services,C=US (CA) CN=GTS Root R4,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 ECDSA 256 ECDSA-SHA384 7ff31977972c224a76155d13b6d685e3
CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 15 Nov 2023 28 Jan 2028 ECDSA 384 SHA256-RSA 7fe530bf331343bedd821610493d8a1b

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of emc2ai.io. — Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
io. present 38690 8 Verified
emc2ai.io. absent Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
strict-transport-security max-age=31536000; includeSubDomains; preload
content-security-policy default-src 'self';style-src 'self' 'unsafe-inline' https:;script-src 'self' 'unsafe-inline' 'unsafe-eval';img-src 'self' data: blob: https: http:;font-src 'self' https: data:;connect-src 'self' ws: wss: https: http:;media-src 'self' blob: data: https:;object-src 'none';frame-src 'self' https://verify.walletconnect.com https://verify.walletconnect.org;base-uri 'self';form-action 'self';frame-ancestors 'self';script-src-attr 'none';upgrade-insecure-requests
x-content-type-options nosniff
x-frame-options SAMEORIGIN
referrer-policy no-referrer-when-downgrade

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://emc2ai.io/api/mcp Not MCP 200
http (plaintext) http://emc2ai.io/api/mcp HTTPS enforced 301 https://emc2ai.io/api/mcp
MCP tools · 40 exposed · ~4,780 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
analyze_bitcoin ~112

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 several of these — see list_einstein_capabilities.]

NameTypeReqDescription
kindstring–mempool · onchain · brc20 · runes · bridges · staking.
limitnumber–Maximum results (1-100).
NameTypeReqDescription
analysisstring–The written answer, identical to the result's text block. This is the field to read: the rest of the payload is whichever capability answered, and its shape varies by tool and by argument.
availableboolean–True when the analysis ran. False when it did not — no capability matched the arguments, the caller is out of credit, billing was unavailable, or the skill produced nothing. NOT a statement about the…
reasonstring–Why there is no analysis, when `available` is false.
skillstring–Which Einstein capability answered. These tools route onto one of many skills by an enum argument, so this names the branch that actually ran.

No examples provided.

analyze_prediction_markets ~127

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 alternatives exist for several of these — see list_einstein_capabilities.]

NameTypeReqDescription
kindstring–markets · insiders · spread · conviction · longshot_fade.
limitnumber–Maximum results (1-100).
querystring–Topic or market keyword to focus on.
NameTypeReqDescription
analysisstring–The written answer, identical to the result's text block. This is the field to read: the rest of the payload is whichever capability answered, and its shape varies by tool and by argument.
availableboolean–True when the analysis ran. False when it did not — no capability matched the arguments, the caller is out of credit, billing was unavailable, or the skill produced nothing. NOT a statement about the…
reasonstring–Why there is no analysis, when `available` is false.
skillstring–Which Einstein capability answered. These tools route onto one of many skills by an enum argument, so this names the branch that actually ran.

No examples provided.

analyze_token_security ~149

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 balance. Free alternatives exist for several of these — see list_einstein_capabilities.]

NameTypeReqDescription
chainstring–Blockchain network.
kindstring–rug_pull = honeypot/rug risk scan · holders = concentration · sniping = launch-sniper activity · approvals = risky token approvals for a wallet · contract_audit = full source audit.
tokenAddressstringyesToken contract address to analyze.
NameTypeReqDescription
analysisstring–The written answer, identical to the result's text block. This is the field to read: the rest of the payload is whichever capability answered, and its shape varies by tool and by argument.
availableboolean–True when the analysis ran. False when it did not — no capability matched the arguments, the caller is out of credit, billing was unavailable, or the skill produced nothing. NOT a statement about the…
reasonstring–Why there is no analysis, when `available` is false.
skillstring–Which Einstein capability answered. These tools route onto one of many skills by an enum argument, so this names the branch that actually ran.

No examples provided.

analyze_tokenized_stocks ~347

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 on Base AND on Robinhood Chain (~$68M/day of stock-quoted curve volume there — the larger half of this market), who bought a token earliest and who FUNDED those wallets, and which wallets keep entering early and actually realize money. [Paid: $0.25 per call from your Einstein credit balance. Free alternatives exist for several of these — see list_einstein_capabilities.]

NameTypeReqDescription
boardstring–portfolio = deterministic non-executing Coinbase B20 portfolio draft on Base (use `intent`) · float-corner = float concentration + mint window · wrapper-trust = can the wrapper be trusted as COLLATER…
intentstring–Natural-language portfolio objective. Used when board=portfolio; no transactions are executed.
tokenstring–Token contract address. Required when board=early-buyers.
NameTypeReqDescription
analysisstring–The written answer, identical to the result's text block. This is the field to read: the rest of the payload is whichever capability answered, and its shape varies by tool and by argument.
availableboolean–True when the analysis ran. False when it did not — no capability matched the arguments, the caller is out of credit, billing was unavailable, or the skill produced nothing. NOT a statement about the…
reasonstring–Why there is no analysis, when `available` is false.
skillstring–Which Einstein capability answered. These tools route onto one of many skills by an enum argument, so this names the branch that actually ran.

No examples provided.

analyze_wallet ~151

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. Free alternatives exist for several of these — see list_einstein_capabilities.]

NameTypeReqDescription
chainstring–Blockchain network.
kindstring–portfolio = holdings · pnl = profit and loss x-ray · trust = trust score · forgotten = stranded assets · airdrops = unclaimed airdrops · quantum = post-quantum exposure.
walletAddressstringyesWallet address to analyze.
NameTypeReqDescription
analysisstring–The written answer, identical to the result's text block. This is the field to read: the rest of the payload is whichever capability answered, and its shape varies by tool and by argument.
availableboolean–True when the analysis ran. False when it did not — no capability matched the arguments, the caller is out of credit, billing was unavailable, or the skill produced nothing. NOT a statement about the…
reasonstring–Why there is no analysis, when `available` is false.
skillstring–Which Einstein capability answered. These tools route onto one of many skills by an enum argument, so this names the branch that actually ran.

No examples provided.

analyze_youtube_video ~233

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 record when Einstein follows it. `length` sets how much is read: 'standard' the first 15 minutes, 'long' up to 1 hour, 'full' up to 3 hours; a tier longer than the video needs, or an unreadable video, is refused and not charged. [Paid: $0.05–$0.60 per call from your Einstein credit balance. Free alternatives exist for several of these — see list_einstein_capabilities.]

NameTypeReqDescription
lengthstring–How much of the video to read: 'standard' (first 15 min, default), 'long' (up to 1 h), 'full' (up to 3 h).
urlstringyesYouTube video link (youtube.com/watch?v=…, youtu.be/…, /shorts/…, /live/…).
NameTypeReqDescription
analysisstring–The written answer, identical to the result's text block. This is the field to read: the rest of the payload is whichever capability answered, and its shape varies by tool and by argument.
availableboolean–True when the analysis ran. False when it did not — no capability matched the arguments, the caller is out of credit, billing was unavailable, or the skill produced nothing. NOT a statement about the…
reasonstring–Why there is no analysis, when `available` is false.
skillstring–Which Einstein capability answered. These tools route onto one of many skills by an enum argument, so this names the branch that actually ran.

No examples provided.

ask_einstein ~101

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: $1.00 per call from your Einstein credit balance. Free alternatives exist for several of these — see list_einstein_capabilities.]

NameTypeReqDescription
promptstringyesThe question or analysis request, in plain language.
NameTypeReqDescription
analysisstring–The written answer, identical to the result's text block. This is the field to read: the rest of the payload is whichever capability answered, and its shape varies by tool and by argument.
availableboolean–True when the analysis ran. False when it did not — no capability matched the arguments, the caller is out of credit, billing was unavailable, or the skill produced nothing. NOT a statement about the…
reasonstring–Why there is no analysis, when `available` is false.
skillstring–Which Einstein capability answered. These tools route onto one of many skills by an enum argument, so this names the branch that actually ran.

No examples provided.

assess_quantum_risk ~116

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 alternatives exist for several of these — see list_einstein_capabilities.]

NameTypeReqDescription
kindstring–readiness · migration (needs `walletAddress`) · portfolio (needs `walletAddress`).
walletAddressstring–Wallet to assess, for `portfolio`.
NameTypeReqDescription
analysisstring–The written answer, identical to the result's text block. This is the field to read: the rest of the payload is whichever capability answered, and its shape varies by tool and by argument.
availableboolean–True when the analysis ran. False when it did not — no capability matched the arguments, the caller is out of credit, billing was unavailable, or the skill produced nothing. NOT a statement about the…
reasonstring–Why there is no analysis, when `available` is false.
skillstring–Which Einstein capability answered. These tools route onto one of many skills by an enum argument, so this names the branch that actually ran.

No examples provided.

check_content_integrity ~118

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 for several of these — see list_einstein_capabilities.]

NameTypeReqDescription
contentstring–The text to judge, for `judge`.
kindstring–judge = score the `content` you supply · vaults = list scanned vaults.
NameTypeReqDescription
analysisstring–The written answer, identical to the result's text block. This is the field to read: the rest of the payload is whichever capability answered, and its shape varies by tool and by argument.
availableboolean–True when the analysis ran. False when it did not — no capability matched the arguments, the caller is out of credit, billing was unavailable, or the skill produced nothing. NOT a statement about the…
reasonstring–Why there is no analysis, when `available` is false.
skillstring–Which Einstein capability answered. These tools route onto one of many skills by an enum argument, so this names the branch that actually ran.

No examples provided.

check_token_safety ~93

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.

NameTypeReqDescription
chainstring–Chain the contract is deployed on.
contractstringyesToken contract address, 0x-prefixed 40 hex characters.
NameTypeReqDescription
availableboolean–False when this call has no data — a snapshot that is not warm yet, a domain switched off, or an argument that was rejected. NOT an error, and NOT a statement about the market.
chain––Chain it was screened on.
contract––Contract that was screened.
fetchedAt––When the underlying snapshot was refreshed (epoch ms or ISO-8601). Age matters: these are cached reads, not live queries.
flagsarray–Individual risk flags recorded against the contract.
honeypot––True when the cached scan flagged it as a honeypot.
reasonstring–Why the payload is absent, when `available` is false.
result––The raw cached row, for fields this summary does not normalize.
riskLevel––Risk grade recorded by the scan.
screened––FALSE means the contract is not in the cached dataset — "not screened", NOT a clean bill of health. Only a true here makes the other fields meaningful.

No examples provided.

detect_mev ~120

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 of these — see list_einstein_capabilities.]

NameTypeReqDescription
chainstring–Blockchain network.
kindstring–detection = historical MEV · protection = protected routing advice.
timeframestring–Lookback window.
tokenAddressstring–Token to inspect, when relevant.
NameTypeReqDescription
analysisstring–The written answer, identical to the result's text block. This is the field to read: the rest of the payload is whichever capability answered, and its shape varies by tool and by argument.
availableboolean–True when the analysis ran. False when it did not — no capability matched the arguments, the caller is out of credit, billing was unavailable, or the skill produced nothing. NOT a statement about the…
reasonstring–Why there is no analysis, when `available` is false.
skillstring–Which Einstein capability answered. These tools route onto one of many skills by an enum argument, so this names the branch that actually ran.

No examples provided.

find_arbitrage ~109

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 — see list_einstein_capabilities.]

NameTypeReqDescription
chainstring–Blockchain network.
kindstring–flashloan · cross_chain · prediction_market.
limitnumber–Maximum results (1-100).
NameTypeReqDescription
analysisstring–The written answer, identical to the result's text block. This is the field to read: the rest of the payload is whichever capability answered, and its shape varies by tool and by argument.
availableboolean–True when the analysis ran. False when it did not — no capability matched the arguments, the caller is out of credit, billing was unavailable, or the skill produced nothing. NOT a statement about the…
reasonstring–Why there is no analysis, when `available` is false.
skillstring–Which Einstein capability answered. These tools route onto one of many skills by an enum argument, so this names the branch that actually ran.

No examples provided.

find_yield ~136

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. Free alternatives exist for several of these — see list_einstein_capabilities.]

NameTypeReqDescription
chainstring–Blockchain network. `robinhoodchain` covers the Pendle NVDA/PFE markets.
kindstring–defi · pendle · discover · liquidations.
limitnumber–Maximum results (1-100).
NameTypeReqDescription
analysisstring–The written answer, identical to the result's text block. This is the field to read: the rest of the payload is whichever capability answered, and its shape varies by tool and by argument.
availableboolean–True when the analysis ran. False when it did not — no capability matched the arguments, the caller is out of credit, billing was unavailable, or the skill produced nothing. NOT a statement about the…
reasonstring–Why there is no analysis, when `available` is false.
skillstring–Which Einstein capability answered. These tools route onto one of many skills by an enum argument, so this names the branch that actually ran.

No examples provided.

forecast_chart ~152

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 this runs fresh inference and is not limited to four assets. Experimental research feature — not investment advice; use at your own risk. [Paid: $0.65 per call from your Einstein credit balance. Free alternatives exist for several of these — see list_einstein_capabilities.]

NameTypeReqDescription
chainstring–Blockchain network.
timeframestring–Candle interval for the forecast.
tokenstringyesToken symbol or contract address to forecast.
NameTypeReqDescription
analysisstring–The written answer, identical to the result's text block. This is the field to read: the rest of the payload is whichever capability answered, and its shape varies by tool and by argument.
availableboolean–True when the analysis ran. False when it did not — no capability matched the arguments, the caller is out of credit, billing was unavailable, or the skill produced nothing. NOT a statement about the…
reasonstring–Why there is no analysis, when `available` is false.
skillstring–Which Einstein capability answered. These tools route onto one of many skills by an enum argument, so this names the branch that actually ran.

No examples provided.

generate_quantum_key ~133

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 creates no account, connects to no existing wallet and moves no funds. [Paid: $0.25–$2.00 per call from your Einstein credit balance. Free alternatives exist for several of these — see list_einstein_capabilities.]

NameTypeReqDescription
kindstring–wallet · encryption · signing · random (raw QRNG output).
NameTypeReqDescription
analysisstring–The written answer, identical to the result's text block. This is the field to read: the rest of the payload is whichever capability answered, and its shape varies by tool and by argument.
availableboolean–True when the analysis ran. False when it did not — no capability matched the arguments, the caller is out of credit, billing was unavailable, or the skill produced nothing. NOT a statement about the…
reasonstring–Why there is no analysis, when `available` is false.
skillstring–Which Einstein capability answered. These tools route onto one of many skills by an enum argument, so this names the branch that actually ran.

No examples provided.

get_agent_context ~64

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 of these — see list_einstein_capabilities.]

Input schema present but exposes no named parameters.

NameTypeReqDescription
analysisstring–The written answer, identical to the result's text block. This is the field to read: the rest of the payload is whichever capability answered, and its shape varies by tool and by argument.
availableboolean–True when the analysis ran. False when it did not — no capability matched the arguments, the caller is out of credit, billing was unavailable, or the skill produced nothing. NOT a statement about the…
reasonstring–Why there is no analysis, when `available` is false.
skillstring–Which Einstein capability answered. These tools route onto one of many skills by an enum argument, so this names the branch that actually ran.

No examples provided.

get_analyst_accuracy ~80

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 their horizon, and says plainly when the record is too thin to rank.

NameTypeReqDescription
limitnumber–Maximum rows to return (1-25).
NameTypeReqDescription
availableboolean–False when this call has no data — a snapshot that is not warm yet, a domain switched off, or an argument that was rejected. NOT an error, and NOT a statement about the market.
object––Always "source-leaderboard".
pending_calls––Calls made but not yet resolvable.
reasonstring–Why the payload is absent, when `available` is false.
reliability_gate_calls––Graded calls a source needs before it is ranked.
rowsarray–One source per row.
sources_past_gate––Sources that cleared the gate — the only ones whose rate means anything.
sources_tracked––Sources with any graded call.

No examples provided.

get_bitcoin_cycle_position ~37

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

Input schema present but exposes no named parameters.

NameTypeReqDescription
activeAddresses––Active addresses, with a 7d trend.
availableboolean–False when this call has no data — a snapshot that is not warm yet, a domain switched off, or an argument that was rejected. NOT an error, and NOT a statement about the market.
dormantSupplyPct––Share of supply dormant. Null when not in this pass.
exchangeFlow––Exchange inflow/outflow and the net signal.
fetchedAt––When the underlying snapshot was refreshed (epoch ms or ISO-8601). Age matters: these are cached reads, not live queries.
marketCap––Market cap, raw and formatted.
minerRevenue––Miner revenue.
mvrv––MVRV ratio with its cycle signal and 7d trend.
nvt––NVT ratio. Null when the metric is not in this pass.
priceUsd––BTC price, raw and formatted.
realizedCap––Realized cap. Null when not in this pass.
reasonstring–Why the payload is absent, when `available` is false.
source––On-chain data source.
stale––True when the snapshot is past its refresh interval.
timeSeriesarray–History behind the metrics, one point per day.
totalFees––Total fees paid.
txCount––Transaction count.
txVolume––On-chain transaction volume. Null when not in this pass.

No examples provided.

get_congress_trades ~42

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

NameTypeReqDescription
limitnumber–Maximum rows to return (1-25).
NameTypeReqDescription
actionableLongs––Long signals that cleared the scoring gate.
availableboolean–False when this call has no data — a snapshot that is not warm yet, a domain switched off, or an argument that was rejected. NOT an error, and NOT a statement about the market.
count––Disclosures in this pass.
fetchedAt––When the underlying snapshot was refreshed (epoch ms or ISO-8601). Age matters: these are cached reads, not live queries.
limitnumber–Row cap applied to every list in this payload.
longSignalsarray–Scored buy-side signals.
reasonstring–Why the payload is absent, when `available` is false.
sectorAggregatesarray–Disclosed dollars by sector.
shortSignalsarray–Scored sell-side signals; same fields as `longSignals`.
shorts––Short signals.
sources––Per-source status — which filing feeds answered.
stale––True when the snapshot is past its refresh interval.

No examples provided.

get_forecast_accuracy ~138

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 per non-overlapping horizon window), so they are comparable to a 50% coin flip. Use this to decide how much weight to give a forecast.

NameTypeReqDescription
assetstring–Restrict to one asset symbol, e.g. BTC. Omit for the whole board; the response lists every asset that has scored rows.
limitnumber–Maximum scored buckets (1-50).
NameTypeReqDescription
asset––Asset filter applied, or null for every asset.
assetsScoredarray–Assets with a graded record.
availableboolean–False when this call has no data — a snapshot that is not warm yet, a domain switched off, or an argument that was rejected. NOT an error, and NOT a statement about the market.
object––Always "forecast-accuracy".
reasonstring–Why the payload is absent, when `available` is false.
rowsarray–One graded bucket per row.
totalBuckets––Scored asset/interval/model buckets in the whole record.
truncated––Present only when a list was cut to `limit`.

No examples provided.

get_government_contracts ~44

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

NameTypeReqDescription
limitnumber–Maximum rows to return (1-25).
NameTypeReqDescription
actionableLongs––Long signals that cleared the scoring gate.
availableboolean–False when this call has no data — a snapshot that is not warm yet, a domain switched off, or an argument that was rejected. NOT an error, and NOT a statement about the market.
count––Awards in this pass.
fetchedAt––When the underlying snapshot was refreshed (epoch ms or ISO-8601). Age matters: these are cached reads, not live queries.
limitnumber–Row cap applied to every list in this payload.
longSignalsarray–Scored buy-side signals.
reasonstring–Why the payload is absent, when `available` is false.
sectorAggregatesarray–Awarded dollars by sector.
shortSignalsarray–Scored sell-side signals; same fields as `longSignals`.
shorts––Short signals.
sources––Per-source status — which award feeds answered.
stale––True when the snapshot is past its refresh interval.
topScore––Its score, 0-1.
topSector––Its sector.
topTicker––Highest-scoring ticker.
watchlistExpansionarray–Tickers the pass added to the watchlist.

No examples provided.

get_hyperliquid_whales ~127

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 reported NEUTRAL whatever its long/short split (one whale is 100% of the traders holding a coin, which is not a consensus), and any whale accounts that could not be read this pass are reported rather than counted as flat.

NameTypeReqDescription
limitnumber–Maximum rows to return (1-25).
NameTypeReqDescription
availableboolean–False when this call has no data — a snapshot that is not warm yet, a domain switched off, or an argument that was rejected. NOT an error, and NOT a statement about the market.
fetchedAt––Per-leg refresh times — positioning and funding age independently.
funding––Perp funding rates, their extremes, divergences and momentum.
limitnumber–Row cap applied to every list in this payload.
reasonstring–Why the payload is absent, when `available` is false.
truncated––Present only when a list was cut to `limit`.
whales––Whale positioning: the consensus read, the bullish/bearish assets and the traders behind it.

No examples provided.

get_launchpad_radar ~111

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 and others through one feed. Use when asked about new launches, fresh memecoins, or whether a launch is bundled.

NameTypeReqDescription
limitnumber–Rows to return (1-15).
NameTypeReqDescription
availableboolean–False when this call has no data — a snapshot that is not warm yet, a domain switched off, or an argument that was rejected. NOT an error, and NOT a statement about the market.
chain––Chain the screen ran on.
object––Always "launchpad-radar".
reasonstring–Why the payload is absent, when `available` is false.
rowsarray–Launchpad tokens approaching or past migration.

No examples provided.

get_market_sentiment ~63

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.

Input schema present but exposes no named parameters.

NameTypeReqDescription
altcoinSeason––Altcoin-season regime, its 30d/90d indices and the cohort behind them.
availableboolean–False when this call has no data — a snapshot that is not warm yet, a domain switched off, or an argument that was rejected. NOT an error, and NOT a statement about the market.
cmc––CoinMarketCap Fear & Greed index, with a yearly high/low.
crypto––Crypto Fear & Greed index, with yesterday/last-week comparisons.
fetchedAt––Per-source refresh times; the four sources age independently.
reasonstring–Why the payload is absent, when `available` is false.
tradfi––CNN TradFi Fear & Greed index — the equities read, for divergence.

No examples provided.

get_polymarket_whales ~49

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

NameTypeReqDescription
limitnumber–Maximum rows to return (1-25).
NameTypeReqDescription
alertCount––Alerts in this pass.
availableboolean–False when this call has no data — a snapshot that is not warm yet, a domain switched off, or an argument that was rejected. NOT an error, and NOT a statement about the market.
fetchedAt––When the underlying snapshot was refreshed (epoch ms or ISO-8601). Age matters: these are cached reads, not live queries.
highRiskCount––Alerts graded high risk.
insiderScanReport––The scan behind the alerts.
limitnumber–Row cap applied to every list in this payload.
reasonstring–Why the payload is absent, when `available` is false.
stale––True when the snapshot is past its refresh interval.
truncated––Present only when a list was cut to `limit`.

No examples provided.

get_prediction_market_catalysts ~51

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

NameTypeReqDescription
limitnumber–Maximum rows to return (1-25).
NameTypeReqDescription
availableboolean–False when this call has no data — a snapshot that is not warm yet, a domain switched off, or an argument that was rejected. NOT an error, and NOT a statement about the market.
fetchedAt––When the underlying snapshot was refreshed (epoch ms or ISO-8601). Age matters: these are cached reads, not live queries.
limitnumber–Row cap applied to every list in this payload.
matchesarray–Prediction markets whose odds moved against a dated catalyst.
reasonstring–Why the payload is absent, when `available` is false.
stale––True when the snapshot is past its refresh interval.

No examples provided.

get_price_forecast ~131

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 rather than triggering new inference.

NameTypeReqDescription
assetstring–Asset symbol. Only the pre-computed universe is available for free.
intervalstring–Candle interval: 4h looks ~32h ahead, 1d ~7d, 1w ~4w, 1M ~4mo.
NameTypeReqDescription
asset––Asset the forecast covers (BTC, ETH, SOL or BNB).
availableboolean–False when this call has no data — a snapshot that is not warm yet, a domain switched off, or an argument that was rejected. NOT an error, and NOT a statement about the market.
consensus––True when TimesFM and Kronos agree. False means the models DISAGREE and the signal is weak; null means agreement was not recorded.
direction––Projected direction — bullish, bearish or neutral.
driftPct––Projected percentage drift over the interval.
fetchedAt––When the underlying snapshot was refreshed (epoch ms or ISO-8601). Age matters: these are cached reads, not live queries.
interval––Candle interval: 4h, 1d, 1w or 1M.
reasonstring–Why the payload is absent, when `available` is false.
source––Which store the cached run came from.

No examples provided.

get_robinhood_whale_prints ~137

Individual large DEX trades on Robinhood Chain (EVM 4663) — the tokenized equities (NVDA, SPY, HIMS) and Pons memecoin flow, each with its token, side, venue and USD value. Every print is valued through its USDG or ETH leg and cross-checked, so trades priced off a freshly-created pool (which the raw chain data reports in the hundreds of millions) are excluded rather than published. WETH/USDG FX swaps are counted separately instead of dominating the tape.

NameTypeReqDescription
limitnumber–Maximum rows to return (1-25).
NameTypeReqDescription
availableboolean–False when this call has no data — a snapshot that is not warm yet, a domain switched off, or an argument that was rejected. NOT an error, and NOT a statement about the market.
fetchedAt––When the underlying snapshot was refreshed (epoch ms or ISO-8601). Age matters: these are cached reads, not live queries.
limitnumber–Row cap applied to every list in this payload.
prints––The tape and the pass that produced it.
reasonstring–Why the payload is absent, when `available` is false.

No examples provided.

get_smart_money_flow ~44

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

NameTypeReqDescription
limitnumber–Maximum rows to return (1-25).
NameTypeReqDescription
availableboolean–False when this call has no data — a snapshot that is not warm yet, a domain switched off, or an argument that was rejected. NOT an error, and NOT a statement about the market.
droppedRoutineCustody––Transfers dropped as routine custody movement rather than signal.
fetchedAt––When the underlying snapshot was refreshed (epoch ms or ISO-8601). Age matters: these are cached reads, not live queries.
limitnumber–Row cap applied to every list in this payload.
notableTransfersarray–The transfers behind the signal.
overallSignal––Net read across the transfers — accumulating, distributing or neutral.
reasonstring–Why the payload is absent, when `available` is false.
smartMoneyMovesarray–One-line summaries of the same moves.
stale––True when the snapshot is past its refresh interval.

No examples provided.

get_smart_money_inflow ~95

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 position, not a consensus. BSC. Use when asked what smart money is buying or where informed flow is going.

NameTypeReqDescription
limitnumber–Rows to return (1-15).
NameTypeReqDescription
availableboolean–False when this call has no data — a snapshot that is not warm yet, a domain switched off, or an argument that was rejected. NOT an error, and NOT a statement about the market.
chain––Chain the screen ran on.
object––Always "smart-money-inflow".
period––Lookback period.
reasonstring–Why the payload is absent, when `available` is false.
rowsarray–Tokens ranked by smart-money inflow.

No examples provided.

get_social_hype ~107

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 asked what is being talked about, what is trending socially, or how sentiment sits on a token.

NameTypeReqDescription
limitnumber–Rows to return (1-15).
sentimentstring–Filter to one sentiment class.
NameTypeReqDescription
availableboolean–False when this call has no data — a snapshot that is not warm yet, a domain switched off, or an argument that was rejected. NOT an error, and NOT a statement about the market.
chain––Chain the screen ran on.
object––Always "social-hype".
reasonstring–Why the payload is absent, when `available` is false.
rowsarray–Tokens ranked by social hype.
sentiment––Sentiment filter applied.

No examples provided.

get_top_movers ~61

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

NameTypeReqDescription
limitnumber–Maximum rows (1-25).
sidestring–Which end of the board to return.
NameTypeReqDescription
availableboolean–False when this call has no data — a snapshot that is not warm yet, a domain switched off, or an argument that was rejected. NOT an error, and NOT a statement about the market.
crossAsset––Cross-asset ranking plus the universe/cohort sizes it was drawn from.
errorsarray–Legs that failed. A partial answer says so here rather than reading as a quiet market.
fetchedAt––When the underlying snapshot was refreshed (epoch ms or ISO-8601). Age matters: these are cached reads, not live queries.
idSource––Source of the asset identifiers.
limitnumber–Row cap applied to every list in this payload.
perChain––Per-chain movers, keyed by chain.
perChainUnavailable––True when the per-chain leg could not be read.
reasonstring–Why the payload is absent, when `available` is false.
side––Which side was asked for — gainers or losers.
source––Price source behind the cross-asset ranking.
stale––True when the snapshot is past its refresh interval.

No examples provided.

get_trade_signals ~84

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 for several of these — see list_einstein_capabilities.]

NameTypeReqDescription
limitnumber–Maximum results (1-100).
NameTypeReqDescription
analysisstring–The written answer, identical to the result's text block. This is the field to read: the rest of the payload is whichever capability answered, and its shape varies by tool and by argument.
availableboolean–True when the analysis ran. False when it did not — no capability matched the arguments, the caller is out of credit, billing was unavailable, or the skill produced nothing. NOT a statement about the…
reasonstring–Why there is no analysis, when `available` is false.
skillstring–Which Einstein capability answered. These tools route onto one of many skills by an enum argument, so this names the branch that actually ran.

No examples provided.

inspect_onchain ~291

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 diamonds) so the answer describes the implementation that actually executes rather than the delegating stub. `transaction` explains what one transaction did: decoded method and logs, exact integer gas arithmetic including the L1 data fee on OP-stack chains, asset and permission changes, and decoded revert reasons. `flow` follows the money from a transaction or wallet across hops and returns a nodes-and-edges graph where every edge carries a real transaction hash. Read-only; nothing is signed or broadcast. [Paid: $0.25–$0.35 per call from your Einstein credit balance. Free alternatives exist for several of these — see list_einstein_capabilities.]

NameTypeReqDescription
addressstring–Contract or wallet address (0x + 40 hex).
chainstring–Blockchain network.
kindstring–contract = review a deployed contract (needs `address`) · transaction = explain one transaction (needs `txHash`) · flow = trace fund flow from a transaction or wallet.
txHashstring–Transaction hash (0x + 64 hex).
NameTypeReqDescription
analysisstring–The written answer, identical to the result's text block. This is the field to read: the rest of the payload is whichever capability answered, and its shape varies by tool and by argument.
availableboolean–True when the analysis ran. False when it did not — no capability matched the arguments, the caller is out of credit, billing was unavailable, or the skill produced nothing. NOT a statement about the…
reasonstring–Why there is no analysis, when `available` is false.
skillstring–Which Einstein capability answered. These tools route onto one of many skills by an enum argument, so this names the branch that actually ran.

No examples provided.

list_einstein_capabilities ~56

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.

Input schema present but exposes no named parameters.

NameTypeReqDescription
availableboolean–False when this call has no data. NOT an error.
billingobject–How paying works: the billing model, how to top up and how to sign in.
freearray–Tools any caller can use with no account and no charge.
paidarray–Tools that need a signed-in Einstein account with credit.
reasonstring–Why the payload is absent, when `available` is false.

No examples provided.

run_backtest ~126

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 Einstein credit balance. Free alternatives exist for several of these — see list_einstein_capabilities.]

NameTypeReqDescription
assetstring–Asset to backtest against.
kindstring–custom (plain-language rules) · standard · engine · optimize.
strategystringyesPlain-language strategy description or template name.
NameTypeReqDescription
analysisstring–The written answer, identical to the result's text block. This is the field to read: the rest of the payload is whichever capability answered, and its shape varies by tool and by argument.
availableboolean–True when the analysis ran. False when it did not — no capability matched the arguments, the caller is out of credit, billing was unavailable, or the skill produced nothing. NOT a statement about the…
reasonstring–Why there is no analysis, when `available` is false.
skillstring–Which Einstein capability answered. These tools route onto one of many skills by an enum argument, so this names the branch that actually ran.

No examples provided.

scan_launchpads ~105

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 list_einstein_capabilities.]

NameTypeReqDescription
limitnumber–Maximum results (1-100).
timeframestring–Lookback window.
venuestring–Which launch venue to scan.
NameTypeReqDescription
analysisstring–The written answer, identical to the result's text block. This is the field to read: the rest of the payload is whichever capability answered, and its shape varies by tool and by argument.
availableboolean–True when the analysis ran. False when it did not — no capability matched the arguments, the caller is out of credit, billing was unavailable, or the skill produced nothing. NOT a statement about the…
reasonstring–Why there is no analysis, when `available` is false.
skillstring–Which Einstein capability answered. These tools route onto one of many skills by an enum argument, so this names the branch that actually ran.

No examples provided.

scan_market ~171

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 Einstein credit balance. Free alternatives exist for several of these — see list_einstein_capabilities.]

NameTypeReqDescription
chainstring–Blockchain network.
kindstring–top_gainers · movers · alpha_ranked (quality-filtered gainers) · altseason · technicals (needs `token`) · regime (market regime classification).
limitnumber–Maximum results (1-100).
timeframestring–Lookback window.
tokenstring–Token symbol or address, for `technicals`.
NameTypeReqDescription
analysisstring–The written answer, identical to the result's text block. This is the field to read: the rest of the payload is whichever capability answered, and its shape varies by tool and by argument.
availableboolean–True when the analysis ran. False when it did not — no capability matched the arguments, the caller is out of credit, billing was unavailable, or the skill produced nothing. NOT a statement about the…
reasonstring–Why there is no analysis, when `available` is false.
skillstring–Which Einstein capability answered. These tools route onto one of many skills by an enum argument, so this names the branch that actually ran.

No examples provided.

scan_v4_hooks ~236

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 swap, reject a swap, block a liquidity withdrawal), which sit behind an upgradeable proxy, and which hooks no registry has catalogued. Permissions are decoded from the hook address itself, so they describe capability, not intent — most delta-taking hooks are ordinary launchpads. Robinhood Chain is one of the largest Uniswap v4 venues by volume (the share moves week to week) and a large share of its hooked liquidity is uncatalogued. [Paid: $0.25 per call from your Einstein credit balance. Free alternatives exist for several of these — see list_einstein_capabilities.]

NameTypeReqDescription
chainIdnumber–Restrict to one chain. 4663 = Robinhood Chain, 56 = BNB Chain, 1 = Ethereum, 8453 = Base. Omit for all four.
NameTypeReqDescription
analysisstring–The written answer, identical to the result's text block. This is the field to read: the rest of the payload is whichever capability answered, and its shape varies by tool and by argument.
availableboolean–True when the analysis ran. False when it did not — no capability matched the arguments, the caller is out of credit, billing was unavailable, or the skill produced nothing. NOT a statement about the…
reasonstring–Why there is no analysis, when `available` is false.
skillstring–Which Einstein capability answered. These tools route onto one of many skills by an enum argument, so this names the branch that actually ran.

No examples provided.

track_whales ~133

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 exist for several of these — see list_einstein_capabilities.]

NameTypeReqDescription
chainstring–Blockchain network.
limitnumber–Maximum results (1-100).
timeframestring–Lookback window.
venuestring–onchain = large on-chain transfers · hyperliquid = perp whale positioning · smart_money = profitable-wallet cohort.
NameTypeReqDescription
analysisstring–The written answer, identical to the result's text block. This is the field to read: the rest of the payload is whichever capability answered, and its shape varies by tool and by argument.
availableboolean–True when the analysis ran. False when it did not — no capability matched the arguments, the caller is out of credit, billing was unavailable, or the skill produced nothing. NOT a statement about the…
reasonstring–Why there is no analysis, when `available` is false.
skillstring–Which Einstein capability answered. These tools route onto one of many skills by an enum argument, so this names the branch that actually ran.

No examples provided.

Install

How do I install the Agent Einstein — Crypto & Market Intelligence MCP server?

Agent Einstein — Crypto & Market Intelligence is a hosted endpoint at https://emc2ai.io/api/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · emc2ai.io

# add to Claude Code
claude mcp add --transport http io-emc2ai-einstein 'https://emc2ai.io/api/mcp'
Common questions

What is the Agent Einstein — Crypto & Market Intelligence MCP server?

Agent Einstein — Crypto & Market Intelligence is an MCP server listed in the public MCP registry as io.emc2ai/einstein. AI price forecasts, whale flows, market sentiment and prediction signals. 18 tools free, no account. This page covers its hosted endpoint (https://emc2ai.io/api/mcp).

Is the Agent Einstein — Crypto & Market Intelligence MCP server safe to use?

Agent Einstein — Crypto & Market Intelligence scores 78 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Agent Einstein — Crypto & Market Intelligence MCP server expose?

Agent Einstein — Crypto & Market Intelligence exposes 40 tools: get_price_forecast, get_forecast_accuracy, get_market_sentiment, get_top_movers, get_smart_money_flow, and 35 more. Their descriptions and schemas cost roughly 4,780 tokens of context every time the server is loaded.

Does the Agent Einstein — Crypto & Market Intelligence MCP server require authentication?

No. We connected to Agent Einstein — Crypto & Market Intelligence without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the Agent Einstein — Crypto & Market Intelligence MCP server still maintained?

Agent Einstein — Crypto & Market Intelligence is still listed as active in the MCP registry. We last reached this channel on 4 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.