com.emergentphysicslab/waveguard

Est-ce que com.emergentphysicslab/waveguard est sûr ?

Au dernier audit MCP Hub, le serveur MCP « com.emergentphysicslab/waveguard » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Les 19 outils

• waveguard_action_surface≈ 259 tokens

  Score candidate actions and extract robust action zones.

  Paramètres, retour & exemple (6)

  Paramètres

  • training · array · requis
    2+ baseline normal samples used to define the reference profile.
  • field_level · integer · optionnel · 0 | 1
    0 = real scalar field, 1 = complex field.
  • sensitivity · number · optionnel
    Anomaly sensitivity multiplier (default: 1.0).
  • action_tests · array · requis
    1+ candidate actions/scenarios to score against baseline.
  • encoder_type · string · optionnel
    Optional encoder override. Omit to auto-detect.
  • action_labels · array · optionnel
    Optional labels for each action variant.

  Exemple d'appel

  {"name": "waveguard_action_surface", "arguments": {"training": [], "action_tests": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• waveguard_cascade_risk≈ 366 tokens

  Estimate shock propagation and resilience from adjacency-linked entities.

  Paramètres, retour & exemple (8)

  Paramètres

  • entities · array · requis
    2+ entities/nodes participating in the cascade graph.
  • field_level · integer · optionnel · 0 | 1
    Field representation level. Default 1 for graph interaction dynamics.
  • sensitivity · number · optionnel
    Anomaly sensitivity multiplier (default: 1.0).
  • encoder_type · string · optionnel
    Optional encoder override. Omit to auto-detect.
  • shock_indices · array · requis
    Indices of initially shocked entities within the entities array.
  • shock_strength · number · optionnel
    Initial perturbation magnitude injected at shock indices.
  • adjacency_matrix · array · requis
    N×N weighted adjacency matrix describing link strengths between entities.
  • training_context · array · requis
    2+ baseline context samples used for normalization.

  Exemple d'appel

  {"name": "waveguard_cascade_risk", "arguments": {"entities": [], "shock_indices": [], "adjacency_matrix": [], "training_context": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• waveguard_compare≈ 230 tokens

  Compare two data items for structural similarity using physics-based fingerprints. Returns cosine similarity (0–1) and Euclidean distance. Use for duplicate detection, behavioral matching, drift analysis, or checking if two tokens/wallets/contracts are structurally similar. Cosine similarity > 0.95 = very similar. < 0.80 = structurally different.

  Paramètres, retour & exemple (3)

  Paramètres

  • data_a · ? · requis
    First data item to compare.
  • data_b · ? · requis
    Second data item to compare (same type as data_a).
  • encoder_type · string · optionnel · json | numeric | text | timeseries | tabular
    Data encoder. Omit to auto-detect.

  Exemple d'appel

  {"name": "waveguard_compare", "arguments": {"data_a": "texte", "data_b": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• waveguard_counterfactual≈ 294 tokens

  Run baseline plus counterfactual variants and measure verdict/score sensitivity.

  Paramètres, retour & exemple (6)

  Paramètres

  • training · array · requis
    2+ baseline normal samples used to build the reference profile.
  • base_test · ? · requis
    Baseline candidate sample to evaluate before counterfactual perturbations.
  • field_level · integer · optionnel · 0 | 1
    0 = real scalar field (faster), 1 = complex field (richer phase dynamics).
  • sensitivity · number · optionnel
    Anomaly sensitivity multiplier (default: 1.0). Higher values flag more aggressively.
  • encoder_type · string · optionnel
    Optional encoder override. Omit to auto-detect from input structure.
  • counterfactual_tests · array · requis
    1+ perturbed variants of base_test for sensitivity analysis.

  Exemple d'appel

  {"name": "waveguard_counterfactual", "arguments": {"training": [], "base_test": "texte", "counterfactual_tests": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• waveguard_fingerprint≈ 297 tokens

  Get a physics embedding of any data item (52-dim at Level 0, 62-dim at Level 1 with phase statistics). The fingerprint captures structural properties via wave-equation dynamics — useful for similarity search, clustering, baseline comparison, and drift detection. Works on JSON objects, token metrics, wallet activity, trading data, or any structured data. Returns a deterministic vector with labeled dimensions (chi statistics, energy distribution, gradient patterns, and phase coherence at Level 1).

  Paramètres, retour & exemple (3)

  Paramètres

  • data · ? · requis
    Any data item to fingerprint: JSON object, numeric array, string, or structured record.
  • field_level · integer · optionnel · 0 | 1
    0 = real scalar 52-dim (default), 1 = complex field 62-dim.
  • encoder_type · string · optionnel · json | numeric | text | timeseries | tabular | complex_numeric
    Data encoder. Omit to auto-detect.

  Exemple d'appel

  {"name": "waveguard_fingerprint", "arguments": {"data": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• waveguard_health≈ 138 tokens

  Check WaveGuard API health, GPU availability, version, and engine status. No authentication required. Returns status, version, and GPU info.

  Paramètres, retour & exemple (1)

  Paramètres

  • verbose · boolean · optionnel
    Return detailed health info including memory and uptime (default: false).

  Exemple d'appel

  {"name": "waveguard_health", "arguments": {"verbose": true}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• waveguard_instability≈ 290 tokens

  Estimate instability under controlled perturb-and-resolve trials.

  Paramètres, retour & exemple (7)

  Paramètres

  • test · array · requis
    1+ candidate samples to stress-test with perturbation trials.
  • trials · integer · optionnel
    Number of perturbation trials per sample.
  • training · array · requis
    2+ baseline normal samples for reference dynamics.
  • field_level · integer · optionnel · 0 | 1
    0 = real scalar field, 1 = complex field.
  • sensitivity · number · optionnel
    Anomaly sensitivity multiplier (default: 1.0).
  • encoder_type · string · optionnel
    Optional encoder override. Omit to auto-detect.
  • perturbation_strength · number · optionnel
    Relative perturbation amplitude applied during instability assay.

  Exemple d'appel

  {"name": "waveguard_instability", "arguments": {"test": [], "training": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• waveguard_interaction_matrix≈ 244 tokens

  Compute pairwise interaction matrix and cluster decomposition for entities.

  Paramètres, retour & exemple (5)

  Paramètres

  • entities · array · requis
    2+ entities to evaluate for pairwise interaction effects.
  • field_level · integer · optionnel · 0 | 1
    Field representation level. Default 1 for interaction/phase features.
  • sensitivity · number · optionnel
    Anomaly sensitivity multiplier (default: 1.0).
  • encoder_type · string · optionnel
    Optional encoder override. Omit to auto-detect.
  • training_context · array · requis
    2+ baseline context samples used for normalization.

  Exemple d'appel

  {"name": "waveguard_interaction_matrix", "arguments": {"entities": [], "training_context": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• waveguard_market_data≈ 452 tokens

  Fetch live crypto market data from CoinGecko and DexScreener. No external data needed — WaveGuard pulls it for you. Use 'coin_id' for CoinGecko (e.g. 'bitcoin', 'ethereum', 'solana'). Use 'contract_address' for DexScreener (any chain). Use 'search' to find token IDs by name/symbol. Returns: price, volume, market cap, liquidity, price history, OHLC candles — ready to feed into waveguard_token_risk, waveguard_volume_check, or waveguard_price_manipulation.

  Paramètres, retour & exemple (6)

  Paramètres

  • days · integer · optionnel
    Number of days of history (default: 90 for price_history, 30 for ohlc).
  • count · integer · optionnel
    Number of results for top_coins (default: 25).
  • query · string · optionnel
    Search query. Required for search, dex_search.
  • action · string · requis · token_data | price_history | ohlc | top_coins | search | dex_token | dex_search
    What data to fetch: - token_data: full metrics for a CoinGecko coin - price_history: daily prices (for price_manipulation) - ohlc: OHLC candles (for volume_check) - top_coins: top N by market cap (training baseline) - search: find CoinGecko coin IDs - dex_token: DEX data by contract address - dex_search: search DEX pairs
  • coin_id · string · optionnel
    CoinGecko coin ID (e.g. 'bitcoin', 'ethereum'). Required for token_data, price_history, ohlc.
  • contract_address · string · optionnel
    Token contract address (any chain). Required for dex_token.

  Exemple d'appel

  {"name": "waveguard_market_data", "arguments": {"action": "token_data"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• waveguard_mechanism_probe≈ 295 tokens

  Run targeted interventions and rank effect sizes.

  Paramètres, retour & exemple (7)

  Paramètres

  • training · array · requis
    2+ baseline normal samples used to construct the reference profile.
  • base_test · ? · requis
    Baseline candidate sample before interventions.
  • field_level · integer · optionnel · 0 | 1
    0 = real scalar field, 1 = complex field.
  • sensitivity · number · optionnel
    Anomaly sensitivity multiplier (default: 1.0).
  • encoder_type · string · optionnel
    Optional encoder override. Omit to auto-detect.
  • intervention_tests · array · requis
    1+ intervention variants used to estimate effect sizes.
  • intervention_labels · array · optionnel
    Optional labels for intervention variants (same order as intervention_tests).

  Exemple d'appel

  {"name": "waveguard_mechanism_probe", "arguments": {"training": [], "base_test": "texte", "intervention_tests": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• waveguard_multi_horizon_outlook≈ 276 tokens

  Compute horizon-specific anomaly outlook and consistency across windows.

  Paramètres, retour & exemple (6)

  Paramètres

  • horizons · array · requis
    List of horizon lengths (in sequence steps) to evaluate.
  • sequence · array · requis
    Ordered sample sequence used for multi-horizon outlook analysis.
  • training · array · requis
    2+ baseline normal samples used to establish reference behavior.
  • field_level · integer · optionnel · 0 | 1
    0 = real scalar field, 1 = complex field.
  • sensitivity · number · optionnel
    Anomaly sensitivity multiplier (default: 1.0).
  • encoder_type · string · optionnel
    Optional encoder override. Omit to auto-detect.

  Exemple d'appel

  {"name": "waveguard_multi_horizon_outlook", "arguments": {"horizons": [], "sequence": [], "training": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• waveguard_phase_coherence≈ 239 tokens

  Measure coherence/entropy and collapse-risk indicators for candidate data.

  Paramètres, retour & exemple (5)

  Paramètres

  • test · array · requis
    1+ candidate samples to evaluate for phase coherence and entropy.
  • training · array · requis
    2+ baseline normal samples for reference coherence metrics.
  • field_level · integer · optionnel · 0 | 1
    Field representation level. Default 1 for phase-aware analysis.
  • sensitivity · number · optionnel
    Anomaly sensitivity multiplier (default: 1.0).
  • encoder_type · string · optionnel
    Optional encoder override. Omit to auto-detect.

  Exemple d'appel

  {"name": "waveguard_phase_coherence", "arguments": {"test": [], "training": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• waveguard_price_manipulation≈ 272 tokens

  Detect price manipulation in time-series data. Send a price or price+volume history as a numeric array. Early windows define 'normal' trading, recent windows are tested for manipulation patterns (pump-and-dump, spoofing, layering). Example: Send 90 days of closing prices → detect manipulated windows.

  Paramètres, retour & exemple (4)

  Paramètres

  • data · array · requis
    Price time-series array (chronological). At least 20 data points.
  • sensitivity · number · optionnel
    Detection sensitivity (default: 1.5).
  • window_size · integer · optionnel
    Window size (default: 10). Smaller = finer detection.
  • test_windows · integer · optionnel
    Number of recent windows to test (default: half).

  Exemple d'appel

  {"name": "waveguard_price_manipulation", "arguments": {"data": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• waveguard_scan≈ 652 tokens

  Find outliers and anomalies in structured data — ideal as a second step after pulling records from Google Sheets, Airtable, Supabase, Notion databases, HubSpot, Financial APIs, GitHub, NPM, or any source that returns rows of JSON. Fully stateless: send known-good rows as training and suspect rows as test in ONE call. Returns per-row anomaly scores, confidence levels, and the top features explaining WHY each row was flagged. Typical workflow: (1) Pull data from another tool (e.g. Google Sheets, Supabase query, HubSpot deals). (2) Pass the first N rows as training (normal baseline). (3) Pass remaining or new rows as test. (4) Report which rows are anomalous and why. Works on JSON objects, numbers, text, arrays. No separate training step required. Examples: - Spreadsheet QA: Pull 500 sales rows from Sheets → train on first 400 → test last 100 → flag outlier entries - Financial screening: Get ratios for 50 stocks from a financial API → find anomalous ones - CRM hygiene: Pull HubSpot deals → flag deals with unusual discount/value patterns - Dependency audit: Get NPM package metrics → flag packages with anomalous quality scores - Commit review: Pull GitHub commit metadata → flag unusual commit patterns

  Paramètres, retour & exemple (5)

  Paramètres

  • test · array · requis
    1+ data points to check for anomalies — new entries, recent rows, or the subset you want validated. Same type/shape as training. Each sample is scored independently.
  • training · array · requis
    2+ examples of NORMAL/expected data — the known-good baseline. Typically the bulk of rows from a spreadsheet, database query, or API response. All samples should be the same type/shape. More samples = better baseline (10-100 is ideal for tabular data).
  • field_level · integer · optionnel · 0 | 1
    Physics field complexity. 0 = real scalar (default). 1 = complex field (phase-aware, 62-dim fingerprint).
  • sensitivity · number · optionnel
    Anomaly threshold multiplier (default: 2.0). Lower = more sensitive. Higher = less sensitive. Range: 0.5 to 5.0.
  • encoder_type · string · optionnel · json | numeric | text | timeseries | tabular | image | correlation | complex_numeric
    Data encoder type. Omit to auto-detect from data shape.

  Exemple d'appel

  {"name": "waveguard_scan", "arguments": {"test": [], "training": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• waveguard_scan_timeseries≈ 436 tokens

  Detect anomalies in time-series data — use after pulling numeric metrics from monitoring APIs, financial data sources, IoT sensors, or spreadsheet columns. Send a single numeric array and specify a window size. Early windows define 'normal', recent windows are tested for anomalies. Typical workflow: (1) Pull a column of numbers from Sheets, a Supabase time-series table, or a metrics API. (2) Pass the array here. (3) Get back which time windows are anomalous. Examples: - Revenue monitoring: Pull monthly revenue from Sheets → detect anomalous months - Stock screening: Pull 90 days of closing prices → find unusual price windows - Server health: Pull response-time metrics → identify degradation windows - Sensor QA: Pull temperature readings from IoT API → flag sensor drift

  Paramètres, retour & exemple (4)

  Paramètres

  • data · array · requis
    Numeric time-series array, ordered chronologically. Should have at least 3x window_size data points.
  • sensitivity · number · optionnel
    Anomaly sensitivity (default: 1.0). Higher = more sensitive.
  • window_size · integer · optionnel
    Number of data points per window (default: 10). Smaller windows detect finer-grained anomalies.
  • test_windows · integer · optionnel
    Number of most recent windows to test (default: half of total windows). The rest are used as training (normal baseline).

  Exemple d'appel

  {"name": "waveguard_scan_timeseries", "arguments": {"data": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• waveguard_token_risk≈ 269 tokens

  Assess crypto token legitimacy risk. Send metrics from known-good tokens as training (price, volume, holders, liquidity, market_cap, age_days, etc.) and suspect tokens as test. Detects pump-and-dump patterns, fake metrics, and anomalous token profiles. Example: Pull CoinGecko data for 20 established tokens → train. Test a new token → get risk score and which metrics are suspicious.

  Paramètres, retour & exemple (3)

  Paramètres

  • test · array · requis
    1+ suspect token metric objects to evaluate.
  • training · array · requis
    3+ known-good token metric objects. Each should include fields like price, volume_24h, market_cap, holders, liquidity, age_days, etc.
  • sensitivity · number · optionnel
    Risk sensitivity (default: 1.5). Higher = more flags.

  Exemple d'appel

  {"name": "waveguard_token_risk", "arguments": {"test": [], "training": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• waveguard_trajectory_scan≈ 231 tokens

  Analyze sequence drift and regime shifts over ordered samples.

  Paramètres, retour & exemple (5)

  Paramètres

  • sequence · array · requis
    Ordered samples (time sequence) to scan for drift and regime shifts.
  • training · array · requis
    2+ baseline normal samples used to establish the reference regime.
  • field_level · integer · optionnel · 0 | 1
    0 = real scalar field, 1 = complex field.
  • sensitivity · number · optionnel
    Anomaly sensitivity multiplier (default: 1.0).
  • encoder_type · string · optionnel
    Optional encoder override. Omit to auto-detect.

  Exemple d'appel

  {"name": "waveguard_trajectory_scan", "arguments": {"sequence": [], "training": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• waveguard_volume_check≈ 243 tokens

  Detect wash trading and fake volume in OHLCV candle data. Send known-legitimate candles as training and suspect candles as test. Detects artificial volume spikes, suspiciously regular patterns, and manipulated price-volume relationships. Example: Send 100 candles from a liquid pair as baseline, test candles from a suspicious pair.

  Paramètres, retour & exemple (3)

  Paramètres

  • test · array · requis
    1+ suspect candle objects to evaluate.
  • training · array · requis
    3+ OHLCV candle objects from known-legitimate trading. Fields: open, high, low, close, volume.
  • sensitivity · number · optionnel
    Detection sensitivity (default: 1.5).

  Exemple d'appel

  {"name": "waveguard_volume_check", "arguments": {"test": [], "training": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• waveguard_wallet_profile≈ 227 tokens

  Profile wallet behavior against baselines. Send normal wallet transaction patterns as training (tx_count, avg_value, unique_tokens, gas_spent, active_days, etc.) and suspect wallets as test. Detects bot activity, wash trading wallets, and sybil patterns. Example: Profile 50 organic wallets → test 10 suspect addresses.

  Paramètres, retour & exemple (3)

  Paramètres

  • test · array · requis
    1+ suspect wallet profiles to evaluate.
  • training · array · requis
    3+ known-organic wallet activity profiles.
  • sensitivity · number · optionnel
    Detection sensitivity (default: 1.5).

  Exemple d'appel

  {"name": "waveguard_wallet_profile", "arguments": {"test": [], "training": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

https://gpartin--waveguard-api-fastapi-app.modal.run/v2/mcp