Categories › Data & Databases › Vector databases & embeddings
Anomaly detection API powered by physics simulation. Scan any data for outliers.
Remote server: your requests and data go to gpartin--waveguard-api-fastapi-app.modal.run. Claude Code: claude mcp add --transport http waveguard https://gpartin--waveguard-api-fastapi-app.modal.run/v2/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
waveguard_scan — Find outliers and anomalies in structured data — ideal as a second step after pulling records from Google Sheets, Airtable, Supabase, Notionwaveguard_scan_timeseries — Detect anomalies in time-series data — use after pulling numeric metrics from monitoring APIs, financial data sources, IoT sensors, or spreawaveguard_health — Check WaveGuard API health, GPU availability, version, and engine status. No authentication required. Returns status, version, and GPU info.waveguard_fingerprint — 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 pwaveguard_compare — Compare two data items for structural similarity using physics-based fingerprints. Returns cosine similarity (0–1) and Euclidean distance. Uwaveguard_token_risk — Assess crypto token legitimacy risk. Send metrics from known-good tokens as training (price, volume, holders, liquidity, market_cap, age_daywaveguard_wallet_profile — Profile wallet behavior against baselines. Send normal wallet transaction patterns as training (tx_count, avg_value, unique_tokens, gas_spenwaveguard_volume_check — Detect wash trading and fake volume in OHLCV candle data. Send known-legitimate candles as training and suspect candles as test. Detects artwaveguard_price_manipulation — Detect price manipulation in time-series data. Send a price or price+volume history as a numeric array. Early windows define 'normal' tradinwaveguard_market_data — Fetch live crypto market data from CoinGecko and DexScreener. No external data needed — WaveGuard pulls it for you. Use 'coin_id' for CoinGewaveguard_counterfactual — Run baseline plus counterfactual variants and measure verdict/score sensitivity.waveguard_trajectory_scan — Analyze sequence drift and regime shifts over ordered samples.waveguard_instability — Estimate instability under controlled perturb-and-resolve trials.waveguard_phase_coherence — Measure coherence/entropy and collapse-risk indicators for candidate data.waveguard_interaction_matrix — Compute pairwise interaction matrix and cluster decomposition for entities.waveguard_cascade_risk — Estimate shock propagation and resilience from adjacency-linked entities.waveguard_mechanism_probe — Run targeted interventions and rank effect sizes.waveguard_action_surface — Score candidate actions and extract robust action zones.waveguard_multi_horizon_outlook — Compute horizon-specific anomaly outlook and consistency across windows.Not tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.