// MCP TOOL REFERENCE

WAVEGUARD TOOLS

19 tools from the WaveGuard MCP Server, categorised by risk level.

View the WaveGuard policy → Token cost: 4,296 tokens →

// ALL 19 WAVEGUARD TOOLS

READ 14 tools

Read waveguard_action_surface Score candidate actions and extract robust action zones. Read waveguard_cascade_risk Estimate shock propagation and resilience from adjacency-linked entities. Read waveguard_compare Compare two data items for structural similarity using physics-based fingerprints. Returns cosine similarit... Read waveguard_fingerprint Get a physics embedding of any data item (52-dim at Level 0, 62-dim at Level 1 with phase statistics). The ... Read waveguard_health Check WaveGuard API health, GPU availability, version, and engine status. No authentication required. Retur... Read waveguard_instability Estimate instability under controlled perturb-and-resolve trials. Read waveguard_interaction_matrix Compute pairwise interaction matrix and cluster decomposition for entities. Read waveguard_market_data Fetch live crypto market data from CoinGecko and DexScreener. No external data needed — WaveGuard pulls it ... Read waveguard_multi_horizon_outlook Compute horizon-specific anomaly outlook and consistency across windows. Read waveguard_phase_coherence Measure coherence/entropy and collapse-risk indicators for candidate data. Read waveguard_scan Find outliers and anomalies in structured data — ideal as a second step after pulling records from Google S... Read waveguard_scan_timeseries Detect anomalies in time-series data — use after pulling numeric metrics from monitoring APIs, financial da... Read waveguard_trajectory_scan Analyze sequence drift and regime shifts over ordered samples. Read waveguard_volume_check Detect wash trading and fake volume in OHLCV candle data. Send known-legitimate candles as training and sus...

WRITE 3 tools

Write waveguard_price_manipulation Detect price manipulation in time-series data. Send a price or price+volume history as a numeric array. Ear... Write waveguard_token_risk Assess crypto token legitimacy risk. Send metrics from known-good tokens as training (price, volume, holder... Write waveguard_wallet_profile Profile wallet behavior against baselines. Send normal wallet transaction patterns as training (tx_count, a...

EXECUTE 2 tools

Execute waveguard_counterfactual Run baseline plus counterfactual variants and measure verdict/score sensitivity. Execute waveguard_mechanism_probe Run targeted interventions and rank effect sizes.

// FAQ

How many tools does the WaveGuard MCP server have? +

The WaveGuard MCP server exposes 19 tools across 3 categories: Read, Write, Execute.

How do I enforce policies on WaveGuard tools? +

Route the WaveGuard server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard — they are enforced on every call before it reaches the server.

What risk categories do WaveGuard tools fall into? +

WaveGuard tools are categorised as Read (14), Write (3), Execute (2). Each category has a recommended default policy.

Let agents act without letting them run wild.

Route your MCP servers through PolicyLayer and every tool call is checked against your policy before it runs — allow, deny, or require approval. Per-identity grants. Full audit log. Live in minutes.

SECURE YOUR MCP →

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.