{"passport":{"unfragile":{"@version":"1.0","version":"2026-05","artifact":{"id":"smithery_agentidx-zarq-risk","slug":"agentidx-zarq-risk","name":"Zarq","type":"mcp","url":"https://smithery.ai/servers/agentidx/zarq-risk","page_url":"https://unfragile.ai/agentidx-zarq-risk","categories":["mcp-servers","code-review-security"],"tags":["mcp","model-context-protocol","smithery:agentidx/zarq-risk"],"pricing":{"model":"open_source","free":true,"starting_price":null},"status":"active","verified":false},"capabilities":[{"id":"smithery_agentidx-zarq-risk__cap_0","uri":"capability://data.processing.analysis.real.time.crypto.token.trust.scoring","name":"real-time crypto token trust scoring","description":"Generates dynamic trust scores for cryptocurrency tokens by analyzing on-chain and off-chain signals in real-time. Implements a multi-factor scoring algorithm that weights structural indicators (contract age, holder distribution, liquidity depth) and behavioral signals (transaction patterns, whale movements) to produce a single trust metric. Scores update continuously as new blockchain data becomes available, enabling detection of trust degradation before market collapse.","intents":["I need to quickly assess whether a token is safe to invest in before buying","I want to monitor my portfolio holdings for emerging trust signals that indicate risk","I need to compare trust scores across multiple tokens to identify the safest assets"],"best_for":["crypto traders and portfolio managers evaluating token safety","DeFi protocol developers assessing counterparty risk","AI agents building autonomous trading or risk management systems"],"limitations":["Trust scores are probabilistic, not deterministic — historical accuracy depends on market regime and may degrade during black swan events","Real-time scoring requires continuous blockchain indexing, which introduces 30-120 second latency depending on network congestion","Scores only reflect on-chain signals; off-chain regulatory or team reputation risks are not captured","Limited to EVM-compatible chains and tokens with sufficient liquidity history for statistical analysis"],"requires":["MCP client compatible with Model Context Protocol v1.0+","Network access to blockchain RPC endpoints (Ethereum, Polygon, Arbitrum, etc.)","API credentials for token metadata providers (CoinGecko, Etherscan, or equivalent)","Minimum 7 days of historical token data for baseline trust calculation"],"input_types":["token contract address (string)","blockchain network identifier (enum: ethereum, polygon, arbitrum, optimism)","optional: time window for historical analysis (ISO 8601 duration)"],"output_types":["structured JSON with trust_score (0-100 float), confidence_interval, component_scores (object), risk_signals (array), timestamp"],"categories":["data-processing-analysis","safety-moderation","crypto-risk-assessment"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"smithery_agentidx-zarq-risk__cap_1","uri":"capability://data.processing.analysis.structural.risk.signal.detection","name":"structural risk signal detection","description":"Identifies and categorizes structural vulnerabilities in token contracts and ecosystems through pattern matching against known risk archetypes. Analyzes contract code patterns (reentrancy vectors, access control flaws, upgrade mechanisms), token economics (inflationary supply schedules, concentration in team wallets), and ecosystem health (validator/node centralization, bridge security). Returns categorized risk signals with severity levels and remediation guidance.","intents":["I need to identify specific technical vulnerabilities in a token contract before investing","I want to understand what structural risks could cause a token to collapse","I need to flag high-severity risks in my portfolio for immediate attention"],"best_for":["security-conscious crypto investors performing due diligence","DeFi protocol auditors and risk managers","AI agents building automated portfolio risk monitoring systems"],"limitations":["Pattern matching is heuristic-based and may produce false positives for novel contract architectures not in the training set","Cannot detect zero-day vulnerabilities or novel attack vectors not yet documented in risk databases","Requires contract source code to be verified on-chain; unverified contracts receive degraded analysis","Economic risk signals depend on accurate historical data; tokens with limited trading history produce uncertain risk assessments"],"requires":["MCP client with Model Context Protocol support","Access to contract verification services (Etherscan API, Sourcify, or equivalent)","Blockchain RPC endpoint for live contract state queries","Token with at least 30 days of trading history for economic analysis"],"input_types":["token contract address (string)","blockchain network (enum)","optional: risk category filter (array of strings: code-vulnerabilities, economic-risks, ecosystem-risks)"],"output_types":["structured JSON array of risk signals, each containing: signal_type (string), severity (critical|high|medium|low), description (string), affected_component (string), remediation_steps (array), confidence_score (0-100 float)"],"categories":["data-processing-analysis","safety-moderation","crypto-risk-assessment"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"smithery_agentidx-zarq-risk__cap_2","uri":"capability://planning.reasoning.market.distress.prediction","name":"market distress prediction","description":"Forecasts potential token market collapses and distress events by analyzing leading indicators including liquidity withdrawal patterns, holder concentration changes, price volatility spikes, and on-chain transaction anomalies. Uses time-series analysis and anomaly detection to identify when a token's behavior deviates from its historical baseline, signaling impending market stress. Produces probabilistic predictions with confidence intervals and lead time estimates.","intents":["I need early warning when a token I hold is showing signs of impending collapse","I want to identify tokens in distress before the broader market recognizes the problem","I need to set automated alerts for when a token's market health deteriorates"],"best_for":["active crypto traders and portfolio managers seeking alpha through early distress detection","risk managers building early-warning systems for institutional crypto holdings","AI agents implementing autonomous portfolio rebalancing triggered by distress signals"],"limitations":["Predictions are probabilistic with inherent uncertainty; lead time varies from hours to days depending on signal strength and market regime","Black swan events (regulatory bans, exchange hacks, team fraud) may not be detectable from on-chain signals alone","Model accuracy degrades during extreme market volatility or novel market conditions not represented in training data","Requires continuous data collection; gaps in data availability reduce prediction confidence"],"requires":["MCP client with streaming or polling capability for continuous signal updates","Historical price and volume data (minimum 90 days for baseline establishment)","On-chain transaction data access via blockchain RPC or indexing service","Liquidity pool data from DEX subgraphs (The Graph, Uniswap V3 subgraph, etc.)"],"input_types":["token contract address (string)","blockchain network (enum)","optional: prediction horizon (integer hours, default 72)","optional: sensitivity threshold (float 0.5-1.0, default 0.7)"],"output_types":["structured JSON containing: distress_probability (0-100 float), confidence_interval (object with lower/upper bounds), predicted_event_type (enum: liquidity_crisis|holder_exodus|price_collapse|exchange_delisting), estimated_lead_time_hours (integer), supporting_signals (array of signal objects with weights)"],"categories":["planning-reasoning","data-processing-analysis","safety-moderation"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"smithery_agentidx-zarq-risk__cap_3","uri":"capability://data.processing.analysis.multi.dimensional.asset.comparison","name":"multi-dimensional asset comparison","description":"Enables side-by-side comparison of multiple cryptocurrency tokens across security, compliance, economic, and ecosystem dimensions. Normalizes heterogeneous metrics (contract age, audit status, regulatory jurisdiction, liquidity depth, holder distribution, validator decentralization) into a unified comparison matrix. Supports custom weighting of dimensions to reflect user priorities, producing ranked asset lists and visual comparison profiles.","intents":["I need to compare 5 tokens to decide which is safest for my portfolio","I want to see how my current holdings rank against alternatives on security and compliance metrics","I need to build a custom scoring model that weights security more heavily than liquidity for my risk profile"],"best_for":["crypto investors performing comparative due diligence across token candidates","portfolio managers building allocation strategies based on multi-factor risk assessment","AI agents implementing token selection logic for automated portfolio construction"],"limitations":["Comparison quality depends on data availability; tokens with limited on-chain history or unverified contracts receive incomplete profiles","Custom weighting requires domain expertise to avoid creating biased or internally inconsistent scoring models","Normalization across heterogeneous metrics introduces assumptions about metric relationships that may not hold in all market conditions","Comparison snapshots are point-in-time; relative rankings change as tokens evolve"],"requires":["MCP client with Model Context Protocol support","Token contract addresses for all assets to compare (minimum 2, recommended 3-10)","Blockchain network identifiers for each token","Optional: custom weighting configuration (JSON object specifying dimension weights)"],"input_types":["array of token contract addresses (strings)","blockchain network (enum or array of enums if comparing cross-chain)","optional: dimension_weights (object with keys: security, compliance, economics, ecosystem; values 0-1 floats summing to 1.0)","optional: comparison_format (enum: matrix|ranked_list|detailed_profiles)"],"output_types":["structured JSON containing: comparison_matrix (2D array with tokens × dimensions), ranked_tokens (array sorted by composite score), dimension_scores (object mapping each token to dimension-level scores), metadata (timestamp, data_completeness_per_token)"],"categories":["data-processing-analysis","search-retrieval"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"smithery_agentidx-zarq-risk__cap_4","uri":"capability://safety.moderation.compliance.and.regulatory.risk.assessment","name":"compliance and regulatory risk assessment","description":"Evaluates cryptocurrency tokens against regulatory frameworks and compliance standards by analyzing token characteristics (jurisdiction of origin, regulatory status, KYC/AML requirements, securities law implications) and ecosystem governance (DAO structure, upgrade mechanisms, regulatory engagement). Produces compliance risk profiles indicating exposure to regulatory action, delisting risk, or legal challenges. Integrates with regulatory databases and legal precedent repositories.","intents":["I need to understand the regulatory risk of a token before adding it to my portfolio","I want to identify tokens that might face delisting or regulatory action","I need to assess whether a token meets compliance requirements for institutional investment"],"best_for":["institutional crypto investors and asset managers with regulatory compliance requirements","compliance officers evaluating token eligibility for fund portfolios","AI agents building compliance-aware portfolio construction systems"],"limitations":["Regulatory landscape is rapidly evolving; assessments reflect current understanding but may become outdated as new regulations emerge","Compliance risk is jurisdiction-dependent; assessment requires specifying relevant regulatory jurisdictions","Legal analysis is heuristic-based and not a substitute for professional legal counsel","Tokens operating in regulatory gray zones receive uncertain assessments"],"requires":["MCP client with Model Context Protocol support","Token contract address and blockchain network","Optional: target jurisdiction(s) for compliance assessment (array of country codes or regulatory regions)","Access to regulatory databases and legal precedent repositories (integrated or external)"],"input_types":["token contract address (string)","blockchain network (enum)","optional: target_jurisdictions (array of strings: US, EU, UK, Singapore, etc.)","optional: assessment_scope (enum: institutional_investment|retail_trading|fund_inclusion)"],"output_types":["structured JSON containing: compliance_risk_score (0-100 float), regulatory_status (enum: compliant|at_risk|high_risk|unknown), jurisdiction_risks (object mapping jurisdictions to risk levels), delisting_probability (0-100 float), legal_precedents (array of relevant cases), remediation_options (array)"],"categories":["safety-moderation","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"smithery_agentidx-zarq-risk__cap_5","uri":"capability://data.processing.analysis.holder.distribution.and.concentration.analysis","name":"holder distribution and concentration analysis","description":"Analyzes the distribution of token ownership across addresses to identify concentration risks and whale exposure. Calculates metrics including Gini coefficient (wealth inequality), Herfindahl index (market concentration), and holder tier distribution (top 1%, top 10%, etc.). Detects suspicious patterns such as sudden concentration changes, large transfers to exchange wallets, or coordinated holder movements. Provides early signals of potential rug pulls or coordinated dumps.","intents":["I need to check if a token is concentrated in a few whale wallets that could dump on me","I want to detect when large holders are moving tokens to exchanges, signaling potential selling pressure","I need to identify tokens with healthy, distributed ownership vs. those with rug pull risk"],"best_for":["retail and institutional crypto investors assessing rug pull and whale dump risk","portfolio managers monitoring holder concentration changes in their holdings","AI agents implementing automated portfolio risk monitoring"],"limitations":["Analysis is based on on-chain holder addresses; cannot identify beneficial owners behind multi-sig wallets or smart contract addresses","Exchange wallet detection is heuristic-based; some exchange wallets may be misclassified","Historical concentration data requires continuous indexing; gaps in data reduce trend analysis accuracy","Whale movements may be legitimate rebalancing or transfers between user wallets, not necessarily selling pressure"],"requires":["MCP client with Model Context Protocol support","Token contract address and blockchain network","Full token transfer history (requires blockchain indexing service or RPC with trace APIs)","Optional: exchange wallet database for detecting exchange deposits"],"input_types":["token contract address (string)","blockchain network (enum)","optional: time_window (ISO 8601 duration, default P30D for last 30 days)","optional: concentration_threshold (float 0-1, default 0.8 for top 80% concentration)"],"output_types":["structured JSON containing: gini_coefficient (0-1 float), herfindahl_index (0-1 float), holder_tiers (object with top_1_percent, top_10_percent, top_100_percent metrics), concentration_trend (array of historical snapshots), whale_movements (array of large transfers with timestamps), risk_signals (array of anomalies)"],"categories":["data-processing-analysis","safety-moderation"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"smithery_agentidx-zarq-risk__cap_6","uri":"capability://data.processing.analysis.liquidity.depth.and.slippage.analysis","name":"liquidity depth and slippage analysis","description":"Evaluates token liquidity across DEX and CEX venues by analyzing order book depth, liquidity pool reserves, and historical slippage patterns. Calculates metrics including effective spread, impact of large trades, and liquidity stability over time. Identifies liquidity fragmentation across venues and detects sudden liquidity withdrawals. Provides slippage estimates for trades of various sizes and flags venues with insufficient depth.","intents":["I need to know how much slippage I'll face if I try to sell a large position","I want to identify which DEX has the deepest liquidity for a token","I need to detect when liquidity is being withdrawn from a token, signaling distress"],"best_for":["traders and portfolio managers planning large trades and assessing execution risk","liquidity providers evaluating token suitability for LP positions","AI agents implementing slippage-aware trade execution"],"limitations":["Liquidity analysis is venue-specific; fragmented liquidity across multiple DEXs/CEXs requires aggregating data from multiple sources","Slippage estimates are based on historical patterns and may not account for market impact during volatile periods","Real-time liquidity data requires continuous polling of DEX subgraphs and CEX APIs, introducing latency","Liquidity can change rapidly; snapshots become stale within minutes during volatile markets"],"requires":["MCP client with Model Context Protocol support","Token contract address and blockchain network","Access to DEX subgraph APIs (The Graph, Uniswap V3 subgraph, etc.)","Optional: CEX API access for centralized exchange liquidity data","Historical trade data for slippage pattern analysis (minimum 7 days)"],"input_types":["token contract address (string)","blockchain network (enum)","optional: trade_size (float in token units, for slippage estimation)","optional: venue_filter (array of strings: uniswap_v3, curve, balancer, binance, coinbase, etc.)"],"output_types":["structured JSON containing: total_liquidity_usd (float), liquidity_by_venue (object), effective_spread_bps (float), slippage_estimates (object mapping trade sizes to slippage %), liquidity_stability_score (0-100 float), fragmentation_index (0-1 float), liquidity_trend (array of historical snapshots)"],"categories":["data-processing-analysis","search-retrieval"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"smithery_agentidx-zarq-risk__cap_7","uri":"capability://safety.moderation.contract.audit.and.verification.status.tracking","name":"contract audit and verification status tracking","description":"Monitors and reports on the audit and verification status of token contracts, including formal verification, security audits by reputable firms, bug bounty program participation, and code review coverage. Tracks audit history, identifies gaps in coverage, and flags tokens with unaudited or partially audited contracts. Integrates with audit databases and verification service APIs to provide current status.","intents":["I need to know if a token's contract has been audited by a reputable firm","I want to identify tokens with formal verification or extensive security review","I need to flag tokens with unaudited contracts as higher risk"],"best_for":["security-conscious crypto investors performing due diligence","portfolio managers with audit requirements for fund holdings","AI agents implementing automated audit status checks"],"limitations":["Audit status is point-in-time; contracts may be updated after audit without re-audit","Audit quality varies significantly between firms; presence of audit does not guarantee security","Formal verification is rare and expensive; most tokens lack formal verification","Audit databases may be incomplete or have outdated information"],"requires":["MCP client with Model Context Protocol support","Token contract address and blockchain network","Access to audit databases (Certik, OpenZeppelin, Trail of Bits, etc.)","Contract verification service access (Etherscan, Sourcify, etc.)"],"input_types":["token contract address (string)","blockchain network (enum)"],"output_types":["structured JSON containing: audit_status (enum: audited|partially_audited|unaudited|formally_verified), audits (array of audit objects with firm, date, scope, findings), bug_bounty_program (boolean), code_review_coverage (0-100 float), verification_status (enum), last_update_timestamp"],"categories":["safety-moderation","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0}],"trust":{"score":47,"verified":false,"data_access_risk":"high","permissions":["MCP client compatible with Model Context Protocol v1.0+","Network access to blockchain RPC endpoints (Ethereum, Polygon, Arbitrum, etc.)","API credentials for token metadata providers (CoinGecko, Etherscan, or equivalent)","Minimum 7 days of historical token data for baseline trust calculation","MCP client with Model Context Protocol support","Access to contract verification services (Etherscan API, Sourcify, or equivalent)","Blockchain RPC endpoint for live contract state queries","Token with at least 30 days of trading history for economic analysis","MCP client with streaming or polling capability for continuous signal updates","Historical price and volume data (minimum 90 days for baseline establishment)"],"failure_modes":["Trust scores are probabilistic, not deterministic — historical accuracy depends on market regime and may degrade during black swan events","Real-time scoring requires continuous blockchain indexing, which introduces 30-120 second latency depending on network congestion","Scores only reflect on-chain signals; off-chain regulatory or team reputation risks are not captured","Limited to EVM-compatible chains and tokens with sufficient liquidity history for statistical analysis","Pattern matching is heuristic-based and may produce false positives for novel contract architectures not in the training set","Cannot detect zero-day vulnerabilities or novel attack vectors not yet documented in risk databases","Requires contract source code to be verified on-chain; unverified contracts receive degraded analysis","Economic risk signals depend on accurate historical data; tokens with limited trading history produce uncertain risk assessments","Predictions are probabilistic with inherent uncertainty; lead time varies from hours to days depending on signal strength and market regime","Black swan events (regulatory bans, exchange hacks, team fraud) may not be detectable from on-chain signals alone","builder identity is not verified yet","no observed match outcomes yet"],"rank_breakdown":{"adoption":0.7029607515441192,"quality":0.41,"ecosystem":0.49000000000000005,"match_graph":0.25,"freshness":0.5,"weights":{"adoption":0.25,"quality":0.25,"ecosystem":0.15,"match_graph":0.23,"freshness":0.12}},"observed_outcomes":{"matches":0,"success_rate":0,"avg_confidence":0,"top_intents":[],"last_matched_at":null},"maintenance":{"status":"active","updated_at":"2026-05-24T12:16:25.062Z","last_scraped_at":"2026-05-03T15:18:25.566Z","last_commit":null},"community":{"stars":null,"forks":null,"weekly_downloads":null,"model_downloads":null,"model_likes":null}},"distribution":{"claim_url":"https://unfragile.ai/submit?claim=agentidx-zarq-risk","compare_url":"https://unfragile.ai/compare?artifact=agentidx-zarq-risk"}},"signature":"ZTOG9sO7Q+ReKiYQAyEgRgmSP0K72DoBBQUF9+HG5mCS5/8Zdh5OJjWQikNwIw9eSDS4/dlO2aU9Nbbfpc9hCQ==","signedAt":"2026-06-20T10:45:21.941Z","signedBy":"unfragile.ai","version":1},"_links":{"self":"https://unfragile.ai/api/v1/passport/agentidx-zarq-risk","artifact":"https://unfragile.ai/agentidx-zarq-risk","verify":"https://unfragile.ai/api/v1/verify?slug=agentidx-zarq-risk","publicKey":"https://unfragile.ai/api/v1/trust-passport-public-key","spec":"https://unfragile.ai/trust","schema":"https://unfragile.ai/schema.json","docs":"https://unfragile.ai/docs"}}