{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_88edtxkeugxj","handle":"waveguard","url":"https://wellknown.network/agents/waveguard","links":{"self":"https://wellknown.network/agents/waveguard/record.json","html":"https://wellknown.network/agents/waveguard","markdown":"https://wellknown.network/agents/waveguard/record.md","api":"https://wellknown.network/api/v1/agents/waveguard","status":"https://wellknown.network/api/v1/agents/waveguard/status","claim":"https://wellknown.network/agents/waveguard/claim","claimApi":"https://wellknown.network/api/v1/claims","badge":"https://wellknown.network/agents/waveguard/badge.svg","openapi":"https://wellknown.network/openapi.json"},"ard":{"identifier":"urn:air:gpartin--waveguard-api-fastapi-app.modal.run:server:waveguard","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"WaveGuard","summary":"Anomaly detection API powered by physics simulation. Scan any data for outliers.","description":"Anomaly detection API powered by physics simulation. Scan any data for outliers.","publisher":{"name":"com.emergentphysicslab","url":null},"homepage":"https://github.com/gpartin/WaveGuardClient","repository":"https://github.com/gpartin/LFMAnomalyDetection","version":"3.1.0","license":null,"protocols":["mcp"],"tags":[],"pricing":null,"endpoints":[{"url":"https://gpartin--waveguard-api-fastapi-app.modal.run/v2/mcp","type":"mcp_streamable_http","auth":null,"probeable":true}],"skills":null,"tools":null,"extra":{"updatedAt":"2026-02-26T10:27:58.916746Z","publishedAt":"2026-02-26T10:27:58.916746Z","registryName":"com.emergentphysicslab/waveguard"},"attribution":{"kind":"mcp_registry","name":"mcp_registry","repoUrl":"mcp_registry","summary":"mcp_registry","version":"mcp_registry","description":"mcp_registry","homepageUrl":"mcp_registry","publisherName":"mcp_registry"}},"derived":{"capabilities":[{"slug":"documents.spreadsheets","name":"Spreadsheets","confidence":1,"provenance":"derived"},{"slug":"data.database","name":"Databases","confidence":1,"provenance":"derived"},{"slug":"finance.markets","name":"Markets & Trading","confidence":1,"provenance":"derived"},{"slug":"documents.ocr","name":"OCR","confidence":0.833,"provenance":"derived"},{"slug":"documents.extraction","name":"Data Extraction","confidence":0.583,"provenance":"derived"},{"slug":"security.identity","name":"Identity & Access","confidence":0.583,"provenance":"derived"},{"slug":"dev.monitoring","name":"Monitoring & Observability","confidence":0.554,"provenance":"derived"},{"slug":"commerce.pricing","name":"Pricing & Quotes","confidence":0.525,"provenance":"derived"}],"categories":["commerce","data","dev","documents","finance","security"]},"observed":{"status":"live","statusReason":"Responded 1h ago.","lastOkAt":"2026-09-05T20:26:05.056Z","lastProbedAt":"2026-09-05T20:26:05.056Z","statusComputedAt":"2026-09-05T20:26:18.809Z","reliability30d":{"probes":1,"successRate":1,"p50Ms":2673},"latestObservations":[{"at":"2026-09-05T20:26:05.056Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":2673,"error":null,"detail":{"tools":[{"name":"waveguard_scan","description":"Find outliers and anomalies in structured data — ideal as a second step after pulling records from Google Sheets, Airtable, Supabase, Notion databases, HubSpot,"},{"name":"waveguard_scan_timeseries","description":"Detect anomalies in time-series data — use after pulling numeric metrics from monitoring APIs, financial data sources, IoT sensors, or spreadsheet columns. Send"},{"name":"waveguard_health","description":"Check WaveGuard API health, GPU availability, version, and engine status. No authentication required. Returns status, version, and GPU info."},{"name":"waveguard_fingerprint","description":"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-e"},{"name":"waveguard_compare","description":"Compare two data items for structural similarity using physics-based fingerprints. Returns cosine similarity (0–1) and Euclidean distance. Use for duplicate det"},{"name":"waveguard_token_risk","description":"Assess crypto token legitimacy risk. Send metrics from known-good tokens as training (price, volume, holders, liquidity, market_cap, age_days, etc.) and suspect"},{"name":"waveguard_wallet_profile","description":"Profile wallet behavior against baselines. Send normal wallet transaction patterns as training (tx_count, avg_value, unique_tokens, gas_spent, active_days, etc."},{"name":"waveguard_volume_check","description":"Detect wash trading and fake volume in OHLCV candle data. Send known-legitimate candles as training and suspect candles as test. Detects artificial volume spike"},{"name":"waveguard_price_manipulation","description":"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 ar"},{"name":"waveguard_market_data","description":"Fetch live crypto market data from CoinGecko and DexScreener. No external data needed — WaveGuard pulls it for you.\n\nUse 'coin_id' for CoinGecko (e.g. 'bitcoin'"},{"name":"waveguard_counterfactual","description":"Run baseline plus counterfactual variants and measure verdict/score sensitivity."},{"name":"waveguard_trajectory_scan","description":"Analyze sequence drift and regime shifts over ordered samples."},{"name":"waveguard_instability","description":"Estimate instability under controlled perturb-and-resolve trials."},{"name":"waveguard_phase_coherence","description":"Measure coherence/entropy and collapse-risk indicators for candidate data."},{"name":"waveguard_interaction_matrix","description":"Compute pairwise interaction matrix and cluster decomposition for entities."},{"name":"waveguard_cascade_risk","description":"Estimate shock propagation and resilience from adjacency-linked entities."},{"name":"waveguard_mechanism_probe","description":"Run targeted interventions and rank effect sizes."},{"name":"waveguard_action_surface","description":"Score candidate actions and extract robust action zones."},{"name":"waveguard_multi_horizon_outlook","description":"Compute horizon-specific anomaly outlook and consistency across windows."}],"toolCount":19,"serverName":"waveguard","capabilities":["tools","prompts"],"serverVersion":"3.3.0","protocolVersion":"2024-11-05"}}],"tools":[{"name":"waveguard_scan","description":"Find outliers and anomalies in structured data — ideal as a second step after pulling records from Google Sheets, Airtable, Supabase, Notion databases, HubSpot,"},{"name":"waveguard_scan_timeseries","description":"Detect anomalies in time-series data — use after pulling numeric metrics from monitoring APIs, financial data sources, IoT sensors, or spreadsheet columns. Send"},{"name":"waveguard_health","description":"Check WaveGuard API health, GPU availability, version, and engine status. No authentication required. Returns status, version, and GPU info."},{"name":"waveguard_fingerprint","description":"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-e"},{"name":"waveguard_compare","description":"Compare two data items for structural similarity using physics-based fingerprints. Returns cosine similarity (0–1) and Euclidean distance. Use for duplicate det"},{"name":"waveguard_token_risk","description":"Assess crypto token legitimacy risk. Send metrics from known-good tokens as training (price, volume, holders, liquidity, market_cap, age_days, etc.) and suspect"},{"name":"waveguard_wallet_profile","description":"Profile wallet behavior against baselines. Send normal wallet transaction patterns as training (tx_count, avg_value, unique_tokens, gas_spent, active_days, etc."},{"name":"waveguard_volume_check","description":"Detect wash trading and fake volume in OHLCV candle data. Send known-legitimate candles as training and suspect candles as test. Detects artificial volume spike"},{"name":"waveguard_price_manipulation","description":"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 ar"},{"name":"waveguard_market_data","description":"Fetch live crypto market data from CoinGecko and DexScreener. No external data needed — WaveGuard pulls it for you.\n\nUse 'coin_id' for CoinGecko (e.g. 'bitcoin'"},{"name":"waveguard_counterfactual","description":"Run baseline plus counterfactual variants and measure verdict/score sensitivity."},{"name":"waveguard_trajectory_scan","description":"Analyze sequence drift and regime shifts over ordered samples."},{"name":"waveguard_instability","description":"Estimate instability under controlled perturb-and-resolve trials."},{"name":"waveguard_phase_coherence","description":"Measure coherence/entropy and collapse-risk indicators for candidate data."},{"name":"waveguard_interaction_matrix","description":"Compute pairwise interaction matrix and cluster decomposition for entities."},{"name":"waveguard_cascade_risk","description":"Estimate shock propagation and resilience from adjacency-linked entities."},{"name":"waveguard_mechanism_probe","description":"Run targeted interventions and rank effect sizes."},{"name":"waveguard_action_surface","description":"Score candidate actions and extract robust action zones."},{"name":"waveguard_multi_horizon_outlook","description":"Compute horizon-specific anomaly outlook and consistency across windows."}],"package":null},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"mcp_registry","key":"com.emergentphysicslab/waveguard","url":"https://registry.modelcontextprotocol.io/v0/servers/com.emergentphysicslab%2Fwaveguard","firstSeenAt":"2026-09-05T18:20:04.380Z","fetchedAt":"2026-09-05T18:20:04.380Z","normalizedAt":"2026-09-05T18:20:04.380Z"}]},"firstSeenAt":"2026-09-05T18:20:04.380Z","updatedAt":"2026-09-05T20:26:28.267Z"}