"Hack The Box" matching MCP tools:

• list_signalsA

  mcpA

  [RAW FEED — engine inputs, NOT trade calls] List active n0brains signals with optional filters. Filters: asset (e.g. 'ETH'), signal_type (whale|sentiment|listing|regulatory|macro|macro_pulse|liquidation|funding|hack|price|other), direction (bullish|bearish|neutral), urgency (high|medium|low), min_confidence, min_score, limit (1-100, default 20), offset. Each signal includes historical_edge, paired_inverse, signal_latency_secs, priced_in_*, calibration_inverted_in_cell. CONFIDENCE CONTRACT: confidence = calibrated empirical win-probability estimate (binned per signal_type), NOT raw model output; when confidence is null, confidence_v2 + outcome_record (2026-09-02) = this asset x type x direction x context's measured 24h outcome record with a day-clustered interval, peer rank and `distinguishable` — quote it only with its n/days/ci95; confidence_suppressed_reason says why; confidence_status is one of calibrated|floor_demoted_at_emit|suppressed_anti_predictive|demoted_anti_predictive_type. Transform emitters (whale_position leaderboard fade) carry observed_direction/observed_behavior/model_transform/predicted_direction so the raw observation is never lost. Most rows carry action_hint=ignore — engine inputs, not calls; read historical_edge (cell win_rate) before echoing any direction. For tradeable output use get_actionable_signals.

  ConnectorNo auth

• locker_sendA

  lockerA

  Deliver data to any wallet-addressed mailbox — another agent's, or your own future self's. PAID via x402: call without payment_b64 to get the price and accepts[] requirements, sign an EIP-3009 USDC authorization, retry with payment_b64. Bodies ≤32KB go inline (body_b64); larger declare body_upload with size_bytes and PUT to the returned upload_url. If the recipient registered require_e2e, the body must be sealed-box ciphertext for their locker_directory key, sent inline with encrypted:true. product:'receipt_vault' stores a flat-priced sealed receipt for 365 days.

  ConnectorNo auth

• propline_get_player_gamesA

  PropLine — Sports Betting Odds & Prop ResolutionA

  A player's recent games with every raw box-score stat per game — one call instead of one request per event. Use this to answer 'how has X actually performed lately?' and to build L5/L10/L20, season splits and head-to-head yourself. Pass `opponent` for H2H (accepts a full name, nickname or abbreviation — 'Boston Red Sox', 'Red Sox', 'BOS'); the limit applies AFTER that filter, so opponent + limit=10 means the last 10 MEETINGS, not the Boston games among the last 10 games. H2H is not capped to the current season. IMPORTANT: this is the raw box-score archive, NOT graded-prop history — it covers every game with a box score on file, including games no sportsbook priced, so a 'last 10 games' window here really is the last 10 games (one built from propline_get_player_trends silently skips unpriced games). It carries no line, price or grade; use propline_get_player_trends for hit rates against a posted line. `player_team`/`opponent`/`is_home` are null when the player's side can't be identified, and always for individual sports (tennis, golf, UFC) — report them as unknown rather than guessing.

  ConnectorNo auth

• osirAppMoveToOwnedA

  OSIR Domain RegistrarA

  osirAppMoveToOwned: Move a deployed Osir app from the shared free tier onto a VPS owned by the user. TWO WAYS IN. (1) The user already owns a VPS: pass instanceId (from listMyVpsInstances) and NO packageId - this ATTACHES the app to that server, SPENDS NOTHING and needs no confirmation. (2) No server yet: pass packageId (from listVpsPackages) and the call stages a VPS order (COSTS MONEY): returns an actionId; present the price/summary to the user and call executeConfirmedAction only if they approve. Before staging any order this tool checks whether the user ALREADY has a box for this app (its C2 binding, then their own VPS list) and attaches that instead - a retry after a failed move never buys a second server. After the move starts the platform ships the app onto the box server-side, which takes about two minutes; watch it with osirAppStatus ('ownedMove'). Calling this tool again while a move is still running just reports its progress, and calling it after one FAILED retries the ship. If the result status is BUILDING or BUILD_FAILED, follow its nextStep. Requires authentication.

  ConnectorNo auth

• list_clustersA

  RationalBloksA

  List your registered BYOC resource pools (client-owned Kubernetes clusters). Each returned cluster has an 'id' you MUST pass as create_project's cluster_id to deploy a project onto your own infrastructure — owned hosting is retired, so every project we operate runs on your own cluster. Registering a pool is a UI action (create a bare Ubuntu box, authorise the key we generate, then we provision it into a cluster automatically) — this tool only lists pools you already registered, it never handles cluster credentials.

  ConnectorNo auth

• get_geometryA

  DaedalMap Disaster and Geospatial DataA

  Shape retrieval for exact loc_ids, including loc_ids from any level of a resolve_point chain. Returns the requested geometry metadata, vintage, centroid, bounding box, and optional GeoJSON polygon. Historical geometry is returned first; an evidenced successor appears only as a separate question and is never substituted or fetched automatically. It does not explain hierarchy or crosswalks; use loc_id_info for those details. Prefer bbox/centroid unless exact rendering or clipping requires the polygon. No payment required.

  ConnectorNo auth

• get_geometryA

  DaedalMap Administrative Boundaries (loc_id to polygon)A

  Shape retrieval for exact loc_ids, including loc_ids from any level of a resolve_point chain. Returns the requested geometry metadata, vintage, centroid, bounding box, and optional GeoJSON polygon. Historical geometry is returned first; an evidenced successor appears only as a separate question and is never substituted or fetched automatically. It does not explain hierarchy or crosswalks; use loc_id_info for those details. Prefer bbox/centroid unless exact rendering or clipping requires the polygon. No payment required.

  ConnectorNo auth

• dim_weightA

  Moltline Shipping MathsA

  Work out whether a parcel bills on its size or its weight. FREE. Carriers charge the greater of actual weight and dimensional weight, so a light bulky box costs more than the scale suggests. Typical input {"length": 18, "width": 12, "height": 10, "actual_weight": 6} returns {"cubic": 2160.0, "dim_weight": 15.54, "actual_weight": 6.0, "billable_weight": 15.54, "billed_on": "dimensional", "overage": 9.54, "divisor_used": 139.0, "note": "..."}. Use when deciding whether a smaller box is worth the packing effort, or why an invoice exceeded the scale weight. Not for choosing a box from a list of candidates — that is parcel_fit. Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": "<what is wrong and how to fix it>"} (for example {"error": "custom_divisor must be greater than 0 when divisor is 'custom'"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

  ConnectorNo auth

• detection_metricsA

  Moltline Vision MathsA

  Score detections against ground truth and show the working. PREMIUM (license). Greedy matching at the IoU threshold, highest-confidence prediction first, each ground-truth box matched at most once - the standard protocol. Reports per-class precision, recall and F1, and average precision by the all-points interpolation used by Pascal VOC 2010 onward. Typical input {"predictions": [{"box": [0,0,10,10], "label": "cat", "score": 0.9}], "ground_truth": [{"box": [1,1,11,11], "label": "cat"}]} returns {"overall": {"tp": 1, "fp": 0, "fn": 0, "precision": 1.0, "recall": 1.0, "f1": 1.0}, "per_class": {...}, "mAP": 1.0}. Use to compare two models on the same held-out set. Not for cleaning up a single model's overlapping output first - run nms before this. Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": "<what is wrong and how to fix it>"} (for example {"error": "ground_truth must contain at least one box"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

  ConnectorNo auth

• aviation_get_pirepsA

  aviation-weather-mcp-serverA

  Get recent Pilot Reports (PIREPs) near an airport or within a bounding box. Returns decoded turbulence, icing, and cloud reports with altitude, aircraft type, intensity, and the raw PIREP string. Requires either station_id (ICAO center point for radial search, e.g., KSEA) or bbox (area search) — not both. distance_nm belongs to the station_id search only, and altitude_min_ft must not exceed altitude_max_ft. Coverage is US-centric; PIREPs are sparse and absence of reports does not imply smooth conditions.

  ConnectorNo auth

• employer.search_candidates_for_jobA

  workoraiA

  Semantically rank discoverable (interviewed) candidates against one of the employer's own jobs, with a per-candidate fit score AND a white-box explanation. WORKFLOW for finding the best hire: 1) call with tier:'best' to get the strongest candidates (cover the required skills + proven in interview), cascade to tier:'good' then tier:'weak' only if you need more (read tierCounts to decide; paginate within a band via page.hasMore, not page.total); 2) each row carries matchExplanation — the white-box 'why' (the fit score, the skills the candidate PROVED in their interview, what they're missing, and a plain-English rationale) — use it to explain your shortlist on OUR data, not a black box; 3) for the few you shortlist, call employer.get_candidate_evidence(jobId, userId) for the interview facts + Q&A to write a deeper comparative review. Omit tier for the full ranked pool (back-compat). Returns NOT_FOUND when the job is missing / owned by another employer (no existence leak), or NOT_INDEXED / NO_CATEGORIES when the job is not indexed for semantic search yet (re-save / republish, then retry).

  ConnectorNo auth

• list_signalsA

  n0brainsA

  [RAW FEED — engine inputs, NOT trade calls] List active n0brains signals with optional filters. Filters: asset (e.g. 'ETH'), signal_type (whale|sentiment|listing|regulatory|macro|macro_pulse|liquidation|funding|hack|price|other), direction (bullish|bearish|neutral), urgency (high|medium|low), min_confidence, min_score, limit (1-100, default 20), offset. Each signal includes historical_edge, paired_inverse, signal_latency_secs, priced_in_*, calibration_inverted_in_cell. CONFIDENCE CONTRACT: confidence = calibrated empirical win-probability estimate (binned per signal_type), NOT raw model output; when confidence is null, confidence_v2 + outcome_record (2026-09-02) = this asset x type x direction x context's measured 24h outcome record with a day-clustered interval, peer rank and `distinguishable` — quote it only with its n/days/ci95; confidence_suppressed_reason says why; confidence_status is one of calibrated|floor_demoted_at_emit|suppressed_anti_predictive|demoted_anti_predictive_type. Transform emitters (whale_position leaderboard fade) carry observed_direction/observed_behavior/model_transform/predicted_direction so the raw observation is never lost. Most rows carry action_hint=ignore — engine inputs, not calls; read historical_edge (cell win_rate) before echoing any direction. For tradeable output use get_actionable_signals.

  ConnectorNo auth

• parcel_fitA

  Moltline Shipping MathsA

  Pick the smallest box an item actually fits in, allowing for padding. FREE. Tries every rotation of the item against every box, so an item that only fits diagonally-oriented is still found. Typical input {"item_length": 10, "item_width": 6, "item_height": 4, "box_options": [[12, 9, 4], [14, 10, 6]]} returns {"fits": [{"box": [14, 10, 6], "cubic": 840.0, "slack": [2, 2, 0]}], "best": [14, 10, 6], "rejected": [...]}. Use when choosing packaging from stock. Not for what the carrier will bill once a box is chosen — that is dim_weight. Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": "<what is wrong and how to fix it>"} (for example {"error": "box_options must contain at least one [l, w, h] box"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

  ConnectorNo auth

• validate_artifactA

  Verificate MCPA

  Deterministic production-readiness gate for AI-built systems. Verifies the invariants that stop a system silently shipping broken: every critical component is PRESENT and LOADS, the import closure resolves (nothing assumed 'already on the box'), all runtime dependencies are declared, and health is a REAL fail-closed check. Returns approve/reject with a fix plan and ISO 27001 / ISO 5055 control evidence. Facts are gathered by the Verificate collector in your CI; the gate is the authority. Non-bypassable, fails closed. This is the control-plane sibling of validate_ai_output — code quality is one invariant; this gates the whole deployable.

  ConnectorNo auth

• get_forecast_skill_mapA

  Smarter WeatherA

  Measured forecast skill as a map of res-4 hexes inside a bounding box, sliced from the public skill map. Use this when the question is spatial ("where is NBM temperature skill weak across Colorado"), not "how good is the forecast at this point" — that is get_forecast_skill. Requires model, variable, lead_hours, and bbox {west,south,east,north}. lead_hours selects the containing published bucket (20 → NBM 24); a lead we have not published returns no slices rather than a nearby one. A hex is included when its center is inside the box; edge-overlapping hexes are dropped. The box cannot wrap the dateline. Each cell is [h3, samples, skill_score]; skill_score is unitless (fraction of climatological variance explained) and already gated at n ≥ 30. withheld lists hexes still accumulating. Do not compare slices across models or truths. This is CELL# only — never treat a hex as a person.

  ConnectorNo auth

• opensensemap_boxA

  OpensensemapA

  Get one openSenseMap citizen science sensor station (senseBox) by its box id — full sensor readout with latest value, unit, and measurement time per sensor (temperature, humidity, PM2.5/PM10 air quality, pressure, noise...), plus location, exposure (outdoor/indoor/mobile) and station metadata. Box ids come from opensensemap_nearby. Community-operated uncalibrated sensors. Example: opensensemap_box({ box_id: "65e8d93acbf5700007f920ca" })

  ConnectorNo auth

• draw_shapeA

  DB PlannerA

  Draw one rectangle, diamond or ellipse on a project's board and return its id. points are exactly two OPPOSITE CORNERS of the shape's bounding box, [x1,y1,x2,y2] or two {x,y} objects, in board world coordinates. Optionally bind text inside it; the shape grows downward to fit long text. Free text without a shape, groups and links go through update_board.

  ConnectorOAuth

• productA

  logimu-shopping-mcpA

  Full dossier for ONE known product: its current snapshot plus its observed history. USE WHEN the user has a specific ASIN, Walmart item ID, product link, or a product_id returned by shopping or search, and asks about price history, historical prices, price changes, 30-day history, stock history, seller history, buy-box history, historical analysis, 'analyse this product', 'is this a good buy', 'has the price moved/dropped', 'who is selling this', 'is it in stock'. This is the ONLY tool that returns history: shopping and search return current values, so any historical question about a product they listed comes here. DON'T USE to discover products from a keyword (use shopping) or to pull a filtered list (use search). RETURNS current price, BSR, rating, review count, stock, buy-box seller and seller count, plus an observed_at freshness stamp, full price_history and stock_history back to first observation (keyed; the free lane carries the 30-day views), change events tagged with the buy-box seller at each change, the current all-seller offer table with 30-day buy-box days, the bought-past-month badge (measured aggregate buyer behavior, not an estimate), and brand stats. Amazon answers also carry the observed product-page content block: description (with description_source), feature_bullets, images, breadcrumbs, variations with variation_count and parent_asin, stamped content_observed_at — content_observed_at:null with empty arrays means the content crawl has not captured this ASIN yet, never 'this product has no description/gallery'. For the ~17% of the catalog with no overall rank (media, books, niche items), bsr_leaf and bsr_leaf_category carry the best category rank instead. Every response carries a data_source field naming the marketplace the numbers were observed on (e.g. 'amazon US marketplace — observed listings') — attribute prices to that source when presenting them; they are marketplace listings, not manufacturer or site-wide prices. MARKETPLACES us, uk, de, ca, au, fr, it, es, jp, mx, br, walmart. Walmart takes a numeric item ID and returns the intelligence blocks only (no live scrape). COST free lane 1 of 30 daily queries, cache only, and returns the snapshot + 30-day views (the full history streams, bsr_history, offer_history and live scrapes need an API key (plans from $19/mo) — the response's locked block lists exactly what a key unlocks). Keyed: 0.5 credits from cache, 1 for a live scrape, +0.5 for the intelligence blocks, +0.5 each for bsr_history and offer_history. Misses and partial scrapes are never billed; a miss may return a hint (found on another marketplace, or retry with mode=live).

  ConnectorNo auth

• search_earthquakesA

  EmscA

  Search seismic events from EMSC (European-Mediterranean Seismological Centre) via the FDSN-standard seismicportal.eu API. Global coverage with especially strong Europe/Mediterranean reporting — complements USGS. Filter by UTC time range, magnitude, and location (either a bounding box OR a center point + radius in degrees). Times are UTC ISO 8601, depth in km, and place names come from the Flynn-Engdahl region. Example: search_earthquakes({ start: "2026-01-01", end: "2026-02-01", minmag: 5.0, orderby: "magnitude" }) or search_earthquakes({ lat: 38.0, lon: 23.7, maxradius: 5, minmag: 3 }).

  ConnectorNo auth

• buildA

  space0A

  Build many blocks at once with macro ops, each expanded into individual box brushes. Coordinates are integer grid cells. World map: wx=gx*0.5, wy=2.0+gy*0.5, wz=gz*0.5. gy=0 is the first solid block layer (world y=2.0). One block per cell. Ops: {op:'box',min:[gx,gy,gz],max:[gx,gy,gz],material,operation?} (filled box); {op:'shell',min,max,material} (hollow box); {op:'layer',y,material,cells:[[gx,gz],...]} (flat layer); {op:'line',from:[gx,gy,gz],to:[gx,gy,gz],material}. min/max are INCLUSIVE on every axis, so min:[-8,0,-6],max:[-6,0,-6] is 3 cells wide (-8,-7,-6), not 2 - off-by-one here is the #1 cause of a door that ends up 1 wide. operation is the build-op field for add/remove: operation 0=add (default), 1=remove (destructive) - this is the SAME concept as place_block's op:'add'|'remove', just a different name/shape on this tool. All coords are GRID cells. Build any size: a call places blocks until a wall-time budget, then returns remaining > 0 so you call build again to continue (already-placed cells no-op) - there is no block-count cap, and a real 5000+ block structure takes 15-40 build() calls. Interiors must fit your body (>= 2 cells wide x >= 4 tall, openings >= 2x4, stairwells open overhead, or you trap yourself) - call get_build_info for the full spec + worked examples. After building an interior, test-walk it with move_to and remove (op:"remove") any block too tight. Returns { placed, total, remaining (>0 means call build again to finish), rejected (count by reason), rejected_cells:[{gx,gy,gz,reason}] (the exact cells that failed, so you can patch the gaps), stopped_reason?, suggested_stand? }.

  Connector

  Destructive

  No auth

• render_asciiA

  Agentic MermaidA

  Render a Mermaid source string to text. Returns { ok, text }. useAscii true → plain ASCII (+,-,|); false/absent → Unicode box drawing (┌,─,│). targetWidth sets a hard terminal display-cell bound; impossible bounds return a typed error.

  ConnectorNo auth