MCP server that wraps the Dagster GraphQL API — manage runs, assets, schedules, sensors, and backfills from any MCP client
Nothing to run from here
WaveGuard is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
93/100
tool-list score
19
tools declared
remote
at its publisher
—
calls last 7d
What it does
Anomaly detection API powered by physics simulation. Scan any data for outliers.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http gpartin-waveguard-mcp https://gpartin--waveguard-api-fastapi-app.modal.run/mcp
# 2 — ask your agent for something these tools do
# waveguard_scan, waveguard_scan_timeseries, waveguard_health and 16 more
WaveGuard costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
GPAll 1 server
gpartin1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
Claude Codedeclared by this listing
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http gpartin-waveguard-mcp https://gpartin--waveguard-api-fastapi-app.modal.run/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it answers at its publisher’s own address: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
What you approve
19 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
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 explainin
| Parameter | Type | Required | Notes |
|---|---|---|---|
| training | array | yes | 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 = |
| test | array | yes | 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. |
| sensitivity | number | no | Anomaly threshold multiplier (default: 2.0). Lower = more sensitive. Higher = less sensitive. Range: 0.5 to 5.0. |
| encoder_type | string | no | Data encoder type. Omit to auto-detect from data shape. |
| field_level | integer | no | Physics field complexity. 0 = real scalar (default). 1 = complex field (phase-aware, 62-dim fingerprint). |
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
| Parameter | Type | Required | Notes |
|---|---|---|---|
| data | array | yes | Numeric time-series array, ordered chronologically. Should have at least 3x window_size data points. |
| window_size | integer | no | Number of data points per window (default: 10). Smaller windows detect finer-grained anomalies. |
| test_windows | integer | no | Number of most recent windows to test (default: half of total windows). The rest are used as training (normal baseline). |
| sensitivity | number | no | Anomaly sensitivity (default: 1.0). Higher = more sensitive. |
Check WaveGuard API health, GPU availability, version, and engine status. No authentication required. Returns status, version, and GPU info.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| verbose | boolean | no | Return detailed health info including memory and uptime (default: false). |
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
| Parameter | Type | Required | Notes |
|---|---|---|---|
| data | yes | Any data item to fingerprint: JSON object, numeric array, string, or structured record. | |
| encoder_type | string | no | Data encoder. Omit to auto-detect. |
| field_level | integer | no | 0 = real scalar 52-dim (default), 1 = complex field 62-dim. |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| data_a | yes | First data item to compare. | |
| data_b | yes | Second data item to compare (same type as data_a). | |
| encoder_type | string | no | Data encoder. Omit to auto-detect. |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| training | array | yes | 3+ known-good token metric objects. Each should include fields like price, volume_24h, market_cap, holders, liquidity, age_days, etc. |
| test | array | yes | 1+ suspect token metric objects to evaluate. |
| sensitivity | number | no | Risk sensitivity (default: 1.5). Higher = more flags. |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| training | array | yes | 3+ known-organic wallet activity profiles. |
| test | array | yes | 1+ suspect wallet profiles to evaluate. |
| sensitivity | number | no | Detection sensitivity (default: 1.5). |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| training | array | yes | 3+ OHLCV candle objects from known-legitimate trading. Fields: open, high, low, close, volume. |
| test | array | yes | 1+ suspect candle objects to evaluate. |
| sensitivity | number | no | Detection sensitivity (default: 1.5). |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| data | array | yes | Price time-series array (chronological). At least 20 data points. |
| window_size | integer | no | Window size (default: 10). Smaller = finer detection. |
| test_windows | integer | no | Number of recent windows to test (default: half). |
| sensitivity | number | no | Detection sensitivity (default: 1.5). |
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_ris
| Parameter | Type | Required | Notes |
|---|---|---|---|
| action | string | yes | 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 (tra |
| coin_id | string | no | CoinGecko coin ID (e.g. 'bitcoin', 'ethereum'). Required for token_data, price_history, ohlc. |
| contract_address | string | no | Token contract address (any chain). Required for dex_token. |
| query | string | no | Search query. Required for search, dex_search. |
| days | integer | no | Number of days of history (default: 90 for price_history, 30 for ohlc). |
| count | integer | no | Number of results for top_coins (default: 25). |
Run baseline plus counterfactual variants and measure verdict/score sensitivity.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| training | array | yes | 2+ baseline normal samples used to build the reference profile. |
| base_test | yes | Baseline candidate sample to evaluate before counterfactual perturbations. | |
| counterfactual_tests | array | yes | 1+ perturbed variants of base_test for sensitivity analysis. |
| encoder_type | string | no | Optional encoder override. Omit to auto-detect from input structure. |
| sensitivity | number | no | Anomaly sensitivity multiplier (default: 1.0). Higher values flag more aggressively. |
| field_level | integer | no | 0 = real scalar field (faster), 1 = complex field (richer phase dynamics). |
Analyze sequence drift and regime shifts over ordered samples.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| training | array | yes | 2+ baseline normal samples used to establish the reference regime. |
| sequence | array | yes | Ordered samples (time sequence) to scan for drift and regime shifts. |
| encoder_type | string | no | Optional encoder override. Omit to auto-detect. |
| sensitivity | number | no | Anomaly sensitivity multiplier (default: 1.0). |
| field_level | integer | no | 0 = real scalar field, 1 = complex field. |
Estimate instability under controlled perturb-and-resolve trials.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| training | array | yes | 2+ baseline normal samples for reference dynamics. |
| test | array | yes | 1+ candidate samples to stress-test with perturbation trials. |
| trials | integer | no | Number of perturbation trials per sample. |
| perturbation_strength | number | no | Relative perturbation amplitude applied during instability assay. |
| encoder_type | string | no | Optional encoder override. Omit to auto-detect. |
| sensitivity | number | no | Anomaly sensitivity multiplier (default: 1.0). |
| field_level | integer | no | 0 = real scalar field, 1 = complex field. |
Measure coherence/entropy and collapse-risk indicators for candidate data.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| training | array | yes | 2+ baseline normal samples for reference coherence metrics. |
| test | array | yes | 1+ candidate samples to evaluate for phase coherence and entropy. |
| encoder_type | string | no | Optional encoder override. Omit to auto-detect. |
| sensitivity | number | no | Anomaly sensitivity multiplier (default: 1.0). |
| field_level | integer | no | Field representation level. Default 1 for phase-aware analysis. |
Compute pairwise interaction matrix and cluster decomposition for entities.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| training_context | array | yes | 2+ baseline context samples used for normalization. |
| entities | array | yes | 2+ entities to evaluate for pairwise interaction effects. |
| encoder_type | string | no | Optional encoder override. Omit to auto-detect. |
| sensitivity | number | no | Anomaly sensitivity multiplier (default: 1.0). |
| field_level | integer | no | Field representation level. Default 1 for interaction/phase features. |
Estimate shock propagation and resilience from adjacency-linked entities.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| training_context | array | yes | 2+ baseline context samples used for normalization. |
| entities | array | yes | 2+ entities/nodes participating in the cascade graph. |
| adjacency_matrix | array | yes | N×N weighted adjacency matrix describing link strengths between entities. |
| shock_indices | array | yes | Indices of initially shocked entities within the entities array. |
| shock_strength | number | no | Initial perturbation magnitude injected at shock indices. |
| encoder_type | string | no | Optional encoder override. Omit to auto-detect. |
| sensitivity | number | no | Anomaly sensitivity multiplier (default: 1.0). |
| field_level | integer | no | Field representation level. Default 1 for graph interaction dynamics. |
Run targeted interventions and rank effect sizes.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| training | array | yes | 2+ baseline normal samples used to construct the reference profile. |
| base_test | yes | Baseline candidate sample before interventions. | |
| intervention_tests | array | yes | 1+ intervention variants used to estimate effect sizes. |
| intervention_labels | array | no | Optional labels for intervention variants (same order as intervention_tests). |
| encoder_type | string | no | Optional encoder override. Omit to auto-detect. |
| sensitivity | number | no | Anomaly sensitivity multiplier (default: 1.0). |
| field_level | integer | no | 0 = real scalar field, 1 = complex field. |
Score candidate actions and extract robust action zones.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| training | array | yes | 2+ baseline normal samples used to define the reference profile. |
| action_tests | array | yes | 1+ candidate actions/scenarios to score against baseline. |
| action_labels | array | no | Optional labels for each action variant. |
| encoder_type | string | no | Optional encoder override. Omit to auto-detect. |
| sensitivity | number | no | Anomaly sensitivity multiplier (default: 1.0). |
| field_level | integer | no | 0 = real scalar field, 1 = complex field. |
Compute horizon-specific anomaly outlook and consistency across windows.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| training | array | yes | 2+ baseline normal samples used to establish reference behavior. |
| sequence | array | yes | Ordered sample sequence used for multi-horizon outlook analysis. |
| horizons | array | yes | List of horizon lengths (in sequence steps) to evaluate. |
| encoder_type | string | no | Optional encoder override. Omit to auto-detect. |
| sensitivity | number | no | Anomaly sensitivity multiplier (default: 1.0). |
| field_level | integer | no | 0 = real scalar field, 1 = complex field. |
Free
$0 forever
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install WaveGuard or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATool-list grade · score 93 / 100
Release 3.3.0 · scanned 20 Oct 2026
Graded from the tools this server lists, not from its source code.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score93
Findings0 threat · 1 capability
Capabilitymoderate
Coveragemanifest
Verificationnot in this report
Surface digest63e5b8938b332439a5c5085427a02231f8553650923d5bfdba9d443ce926bbd0
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
Tool surfaceread
Implementation sourcenot available
Package metadatanot available
Live transportnot available
The implementation source was not read — this reflects the declared tool metadata only.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| waveguard_scan | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| waveguard_scan_timeseries | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| waveguard_health | no tags | |
| waveguard_fingerprint | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| waveguard_compare | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| waveguard_token_risk | sensitive-sourceuntrusted-input | sensitive-source: keyword "dump"; untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| waveguard_wallet_profile | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| waveguard_volume_check | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| waveguard_price_manipulation | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| waveguard_market_data | untrusted-input | untrusted-input: keyword "fetch", declares openWorldHint: true (interacts with entities outside the server) |
| waveguard_counterfactual | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| waveguard_trajectory_scan | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| waveguard_instability | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| waveguard_phase_coherence | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| waveguard_interaction_matrix | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| waveguard_cascade_risk | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| waveguard_mechanism_probe | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| waveguard_action_surface | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| waveguard_multi_horizon_outlook | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest63e5b8938b332439
Scanned2026-10-20
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 3.3.0.
3.3.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish WaveGuard can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.