# Gpartin Waveguard MCP server

Source: https://glimind.com/server/mcp-registry%2Fio.github.gpartin%2Fwaveguard
Registry id: `mcp-registry/io.github.gpartin/waveguard`
Status: live (checked 2026-10-28T02:59:40.382Z)

## Measurements (30 days)

- Uptime: 92.15%
- Checks: 5112
- Outages (90 days): 981

## Install

```json
{
  "mcpServers": {
    "gpartin-waveguard-mcp-server": {
      "type": "http",
      "url": "https://gpartin--waveguard-api-fastapi-app.modal.run/mcp"
    }
  }
}
```

Claude Code:

```sh
claude mcp add --transport http gpartin-waveguard-mcp-server https://gpartin--waveguard-api-fastapi-app.modal.run/mcp
```

## Tools (19)

- `waveguard_action_surface`: Score candidate actions and extract robust action zones.
- `waveguard_cascade_risk`: Estimate shock propagation and resilience from adjacency-linked entities.
- `waveguard_compare`: Compare two data items for structural similarity using physics-based fingerprints. Returns cosine similarity (0–1) and Euclidean distance. Use for duplicate det
- `waveguard_counterfactual`: Run baseline plus counterfactual variants and measure verdict/score sensitivity.
- `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 properties via wave-e
- `waveguard_health`: Check WaveGuard API health, GPU availability, version, and engine status. No authentication required. Returns status, version, and GPU info.
- `waveguard_instability`: Estimate instability under controlled perturb-and-resolve trials.
- `waveguard_interaction_matrix`: Compute pairwise interaction matrix and cluster decomposition for entities.
- `waveguard_market_data`: 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',
- `waveguard_mechanism_probe`: Run targeted interventions and rank effect sizes.
- `waveguard_multi_horizon_outlook`: Compute horizon-specific anomaly outlook and consistency across windows.
- `waveguard_phase_coherence`: Measure coherence/entropy and collapse-risk indicators for candidate data.
- `waveguard_price_manipulation`: 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
- `waveguard_scan`: Find outliers and anomalies in structured data — ideal as a second step after pulling records from Google Sheets, Airtable, Supabase, Notion databases, HubSpot,
- `waveguard_scan_timeseries`: Detect anomalies in time-series data — use after pulling numeric metrics from monitoring APIs, financial data sources, IoT sensors, or spreadsheet columns. Send
- `waveguard_token_risk`: Assess crypto token legitimacy risk. Send metrics from known-good tokens as training (price, volume, holders, liquidity, market_cap, age_days, etc.) and suspect
- `waveguard_trajectory_scan`: Analyze sequence drift and regime shifts over ordered samples.
- `waveguard_volume_check`: 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
- `waveguard_wallet_profile`: Profile wallet behavior against baselines. Send normal wallet transaction patterns as training (tx_count, avg_value, unique_tokens, gas_spent, active_days, etc.

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.