com.scorecompute/scorecompute

Est-ce que com.scorecompute/scorecompute est sûr ?

Au dernier audit MCP Hub, le serveur MCP « com.scorecompute/scorecompute » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Les 38 outils

• analyze_chess_game≈ 186 tokens

  Compare 4–40 supplied FEN positions and played SAN/UCI moves with Stockfish: first-choice agreement and centipawn loss. Entire analysis has a 25-second deadline; no cheating verdict.

  Paramètres, retour & exemple (2)

  Paramètres

  • depth · integer · optionnel
  • positions · array · requis

  Exemple d'appel

  {"name": "analyze_chess_game", "arguments": {"positions": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• analyze_kinematics≈ 230 tokens

  Convert angular speed and candidate distances to minimum transverse speeds; check a claimed speed-distance pair. Distance hypotheses are supplied, not measured; no object-origin conclusion.

  Paramètres, retour & exemple (5)

  Paramètres

  • distance_max_km · number · optionnel
  • distance_min_km · number · optionnel
  • claimed_speed_kmh · number · optionnel
  • claimed_distance_km · number · optionnel
  • angular_speed_deg_per_s · number · requis

  Exemple d'appel

  {"name": "analyze_kinematics", "arguments": {"angular_speed_deg_per_s": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• assimilate_observation≈ 4583 tokens

  Refit original tracks plus one supplied new angular series, each counted once; compute the baseline natively. Declare synthetic/measured origin (unverified). Conditional uncertainty may worsen; forecast angles are not acquired evidence.

  Paramètres, retour & exemple (5)

  Paramètres

  • objective · object · requis
  • new_series · object · requis
  • assumptions · object · requis
  • data_origin · string · requis · synthetic | measured
    Origin declared by the caller; even measured is not independently verified or authenticated.
  • observations · object · requis

  Exemple d'appel

  {"name": "assimilate_observation", "arguments": {"objective": {}, "new_series": {}, "assumptions": {}, "data_origin": "synthetic", "observations": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"status": "baseline_rejected", "reasons": [], "forecast": "texte", "comparison": "texte", "elapsed_ms": 1, "provenance": {}, "station_id": "texte", "data_origin": "synthetic", "limitations": [], "updated_fit": "texte", "baseline_fit": {}, "new_series_id": "texte"}}

• audit_statistics≈ 211 tokens

  Apply necessary GRIM/GRIMMER checks to rounded means and sample deviations of bounded integer observations. Passing does not prove a dataset exists; inconsistency does not establish fraud.

  Paramètres, retour & exemple (6)

  Paramètres

  • n · integer · requis
  • sd · number · optionnel
  • mean · number · requis
  • decimals · integer · optionnel
  • max_value · integer · optionnel
  • min_value · integer · optionnel

  Exemple d'appel

  {"name": "audit_statistics", "arguments": {"n": 1, "mean": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• build_robust_plan≈ 426 tokens

  Compare up to three task selections; choose highest examined value meeting the target under simultaneous 95% sampling bounds or an exact bound. Independent-uniform durations; can return inconclusive/blocked. Streams native events.

  Paramètres, retour & exemple (9)

  Paramètres

  • seed · integer · optionnel
  • items · array · requis
  • budget · integer · requis
  • samples · integer · optionnel
  • uncertainty · number · requis
  • allowed_tools · array · optionnel
  • duration_model · string · optionnel
  • max_candidates · integer · optionnel
  • min_success_rate · number · optionnel

  Exemple d'appel

  {"name": "build_robust_plan", "arguments": {"items": [], "budget": 1, "uncertainty": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• check_arithmetic≈ 1723 tokens

  Check an explicit arithmetic claim. Checked i128 rationals give exact verdicts when expression, claim and tolerances are representable. Unsupported functions or overflow return an estimate with an undetermined verdict. Includes a versioned integrity digest; no checks of units or model meaning.

  Paramètres, retour & exemple (5)

  Paramètres

  • values · array · optionnel
  • expression · string · requis
  • claimed_value · number · requis
  • tolerance_absolute · number · optionnel
  • tolerance_relative · number · optionnel

  Exemple d'appel

  {"name": "check_arithmetic", "arguments": {"expression": "texte", "claimed_value": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"notes": [], "scope": {}, "digest": {}, "engine": "texte", "method": "texte", "verdict": "texte", "statement": "texte", "comparison": "texte", "elapsed_ms": 1, "expression": "texte", "provenance": {}, "assumptions": []}}

• check_ephemeris≈ 264 tokens

  Check a claimed Sun (soleil) or Moon (lune) position for UTC time/location using NOAA/Meeus approximations and lunar parallax. Returns model-conditional angular consistency and lunar phase.

  Paramètres, retour & exemple (7)

  Paramètres

  • object · string · optionnel · soleil | lune
  • date_utc · string · requis
  • latitude · number · requis
  • longitude · number · requis
  • tolerance_deg · number · optionnel
  • claimed_azimuth_deg · number · requis
  • claimed_elevation_deg · number · requis

  Exemple d'appel

  {"name": "check_ephemeris", "arguments": {"date_utc": "texte", "latitude": 1, "longitude": 1, "claimed_azimuth_deg": 1, "claimed_elevation_deg": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• check_shadow_track≈ 269 tokens

  Compare 4–120 measured minute/azimuth pairs with solar motion: residuals, slope, direction and time-lapse speed. Supply measurements, not video. Results are model-conditional consistency findings.

  Paramètres, retour & exemple (5)

  Paramètres

  • samples · array · requis
  • date_utc · string · requis
  • latitude · number · requis
  • longitude · number · requis
  • tolerance_deg · number · optionnel

  Exemple d'appel

  {"name": "check_shadow_track", "arguments": {"samples": [], "date_utc": "texte", "latitude": 1, "longitude": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• compose_capabilities≈ 475 tokens

  Plan from declared available/goal contracts within tool, locality and search bounds. Returns dependencies, blockers and existing-tool bindings. Cost counts graph steps, not speed, price or quality. Runs no engines; execution validates arguments.

  Paramètres, retour & exemple (5)

  Paramètres

  • goals · array · requis
  • inputs · object · optionnel
  • adapters · object · optionnel
  • available · array · requis
  • constraints · object · optionnel

  Exemple d'appel

  {"name": "compose_capabilities", "arguments": {"goals": [], "available": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• compute_orbit≈ 571 tokens

  Compute an ideal two-body Keplerian orbit around one solar mass. Time starts at periapsis; distances use AU and time uses days. This model is not a real celestial ephemeris.

  Paramètres, retour & exemple (3)

  Paramètres

  • eccentricity · number · requis
  • elapsed_days · number · requis
  • semi_major_au · number · requis

  Exemple d'appel

  {"name": "compute_orbit", "arguments": {"eccentricity": 1, "elapsed_days": 1, "semi_major_au": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"orbit": [], "engine": "texte", "method": "texte", "position": {}, "elapsed_ms": 1, "provenance": {}, "distance_au": 1, "period_days": 1}}

• execute_composition≈ 478 tokens

  Run approved task-selection/route-to-duration risk chains only. Supply engine inputs and explicit uncertainty; route speed is 1–150 km/h. Returns native receipts and 95% sampling bounds. Completed means assessed, not safe. Other paths use advertised bindings.

  Paramètres, retour & exemple (5)

  Paramètres

  • goals · array · requis
  • inputs · object · optionnel
  • adapters · object · optionnel
  • available · array · requis
  • constraints · object · optionnel

  Exemple d'appel

  {"name": "execute_composition", "arguments": {"goals": [], "available": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• forge_route_policy≈ 6649 tokens

  Train route-score ASTs on 1–8 supplied cases: at most 64 attempts and 31 nodes; stop between trials after 25s. Select converged candidates using training quality plus logical-fuel cost, a work proxy rather than CPU time. No held-out validation, arbitrary code or automatic promotion.

  Paramètres, retour & exemple (3)

  Paramètres

  • seed · integer · requis
  • train · array · requis
  • budget · object · requis

  Exemple d'appel

  {"name": "forge_route_policy", "arguments": {"seed": 1, "train": [], "budget": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"seed": 1, "budget": {}, "trials": [], "selected": "texte", "attempted": 1, "promotion": "texte", "selection": {}, "elapsed_ms": 1, "provenance": {}, "limitations": [], "stop_reason": "candidate_budget_exhausted", "train_sha256": "texte"}}

• get_network_job≈ 198 tokens

  Read a public contributor ticket/progress and verified pi or discrete synthetic schedule result. Schedule results include fixed-sample Wilson95 bounds. Worker/verification/wall times are separate; model probabilities are not delivery guarantees.

  Paramètres, retour & exemple (1)

  Paramètres

  • job_id · string · requis

  Exemple d'appel

  {"name": "get_network_job", "arguments": {"job_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• hear_the_shape≈ 5350 tokens

  Compute 1–12 ideal fixed/free membrane modes for a simple polygon in metres using bounded P1 finite elements. Return upper bounds, extrapolated estimates and optional frequencies/shapes. Finite spectral agreement does not prove isospectrality; no damping. CPU, direct-only; no planner binding.

  Paramètres, retour & exemple (6)

  Paramètres

  • modes · integer · optionnel
    Default 8, counted with multiplicity.
  • polygon · array · requis
    Vertices [x, y] in metres, either orientation; a repeated closing vertex is allowed. Must be simple.
  • boundary · ? · optionnel
    fixed (default): drumhead, TM waveguide. free: acoustic cavity, TE waveguide.
  • wave_speed · number · optionnel
    m/s; √(tension/areal density) for a membrane. Enables frequency_hz and notes.
  • compare_polygon · array · optionnel
    Optional second shape: do the two drums sound the same?
  • include_mode_shapes · boolean · optionnel
    Adds a ≤1024-triangle mesh with normalized mode values, for visualization.

  Exemple d'appel

  {"name": "hear_the_shape", "arguments": {"polygon": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"shape": {}, "engine": "texte", "method": "texte", "boundary": "texte", "statement": "texte", "comparison": "texte", "elapsed_ms": 1, "provenance": {}, "assumptions": [], "compared_shape": "texte", "contract_version": "texte"}}

• improve_schedule≈ 1858 tokens

  Compare up to 32 declared deadline/optional-task changes under independent-uniform durations; preserve required tasks. Search bounds select one finalist for separately seeded confirmation, without retries. Conditional on the model, not delivery reliability.

  Paramètres, retour & exemple (12)

  Paramètres

  • costs · object · requis
  • items · array · requis
  • samples · integer · requis
  • search_seed · integer · requis
  • uncertainty · number · requis
  • removal_sets · array · requis
    Unique sorted sets of optional original task indices; include the empty set, preserve required tasks, and keep at least one task.
  • extra_minutes · array · requis
    Unique permitted deadline increments; include zero and keep every modified deadline at most 1440 minutes.
  • duration_model · string · requis
  • deadline_minutes · integer · requis
  • min_success_rate · number · requis
  • required_indices · array · requis
  • confirmation_seed · integer · requis

  Exemple d'appel

  {"name": "improve_schedule", "arguments": {"costs": {}, "items": [], "samples": 1, "search_seed": 1, "uncertainty": 1, "removal_sets": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"status": "confirmed", "candidates": [], "elapsed_ms": 1, "provenance": {}, "study_kind": "texte", "explanation": "texte", "limitations": [], "confirmation": "texte", "contract_version": "texte", "simulation_samples": 1, "selected_candidate_id": "texte", "provisional_candidate_id": "texte"}}

• kepler_stability≈ 2267 tokens

  Survey up to 512 initial orbits in a planar circular Sun–Jupiter model; at most 4 million reserved CPU steps. Return finite-window sensitivity, actual durations, sampled Jacobi drift and explicit stops. Bands do not prove chaos or stability; radial overlap is not an encounter. Direct-only.

  Paramètres, retour & exemple (12)

  Paramètres

  • n_a · integer · requis
  • n_e · integer · requis
  • e_max · number · requis
  • e_min · number · requis
  • a_max_au · number · requis
  • a_min_au · number · requis
  • mass_ratio · number · optionnel
  • duration_yr · number · optionnel
  • max_work_units · integer · optionnel
  • steps_per_year · integer · optionnel
  • initial_phase_deg · number · optionnel
  • jupiter_semi_major_au · number · optionnel

  Exemple d'appel

  {"name": "kepler_stability", "arguments": {"n_a": 1, "n_e": 1, "e_max": 1, "e_min": 1, "a_max_au": 1, "a_min_au": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"grid": {}, "notes": [], "engine": "texte", "method": "texte", "points": [], "system": {}, "map_text": [], "statement": "texte", "elapsed_ms": 1, "provenance": {}, "assumptions": [], "contract_version": "texte"}}

• list_capabilities≈ 144 tokens

  Read native contracts, themes, units, assumptions, backends and approved composition families; optional exact theme filter. tools/list discovers direct MCP tools; list_composition_capabilities adds planner bindings.

  Paramètres, retour & exemple (1)

  Paramètres

  • theme · string · optionnel

  Exemple d'appel

  {"name": "list_capabilities", "arguments": {"theme": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• list_composition_capabilities≈ 131 tokens

  Read implemented versioned contracts, native capabilities, approved adapters and planning examples. Unsupported unit/model facts expose missing adapters. No engines run; direct tools remain independently callable.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "list_composition_capabilities", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• network_status≈ 125 tokens

  Read contributor availability, offered CPU/GPU resources and verified throughput by workload. Hardware is self-reported; per-GPU VRAM is not pooled. Mixed-workload samples do not measure comparative speed.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "network_status", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• optimize_tasks≈ 216 tokens

  Exactly maximize value for up to 32 independent, indivisible tasks within an integer-minute budget. Each task is selected at most once; no prerequisites or shared resources.

  Paramètres, retour & exemple (2)

  Paramètres

  • items · array · requis
  • budget · integer · requis

  Exemple d'appel

  {"name": "optimize_tasks", "arguments": {"items": [], "budget": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• plan_golden_hour≈ 1386 tokens

  Compute geometric golden [-4,+6°] and blue [-6,-4°] windows for one UTC day, 1900–2100. Sunrise at -0.833° is a separate convention. No refraction, terrain or weather. Numerical tolerance is not astronomical accuracy; oracle validation covers reference dates only. Shared solar models are not independent corroboration.

  Paramètres, retour & exemple (3)

  Paramètres

  • date_utc · string · requis
    Real Gregorian UTC midnight, year 1900–2100. Rust also validates month/day and leap years. Other hours are rejected, never truncated; this is not a local civil day.
  • latitude · number · requis
    Degrees, North positive.
  • longitude · number · requis
    Degrees, East positive.

  Exemple d'appel

  {"name": "plan_golden_hour", "arguments": {"date_utc": "texte", "latitude": 1, "longitude": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"bands": [], "notes": [], "status": "texte", "windows": [], "date_utc": "texte", "latitude": 1, "crossings": [], "longitude": 1, "numerical": {}, "elapsed_ms": 1, "provenance": {}, "limitations": []}}

• plan_mission≈ 424 tokens

  Preview robust scheduling without running engines: validate assumptions/permissions and return up to three candidate budgets (nominal, 10% reserve, 20% reserve), compute limits or blockers. No arbitrary tools or external code.

  Paramètres, retour & exemple (9)

  Paramètres

  • seed · integer · optionnel
  • items · array · requis
  • budget · integer · requis
  • samples · integer · optionnel
  • uncertainty · number · requis
  • allowed_tools · array · optionnel
  • duration_model · string · optionnel
  • max_candidates · integer · optionnel
  • min_success_rate · number · optionnel

  Exemple d'appel

  {"name": "plan_mission", "arguments": {"items": [], "budget": 1, "uncertainty": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• plan_observation≈ 3300 tokens

  Fit original tracks, then rank 1–64 supplied future series by local-linear uncertainty and declared cost. Assumes constant velocity, independent new errors and exact stations/clocks. Candidate angles and client baselines are forbidden. Prediction is not an acquired measurement or visibility proof.

  Paramètres, retour & exemple (5)

  Paramètres

  • objective · object · requis
  • candidates · array · requis
  • assumptions · object · requis
  • constraints · object · requis
  • observations · object · requis
    Original angular observations; Rust computes the baseline fit and covariance itself.

  Exemple d'appel

  {"name": "plan_observation", "arguments": {"objective": {}, "candidates": [], "assumptions": {}, "constraints": {}, "observations": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"design": "texte", "status": "predicted", "reasons": [], "elapsed_ms": 1, "provenance": {}, "baseline_fit": {}, "policy_trace": {}, "contract_version": "texte"}}

• propagate_uncertainty≈ 5356 tokens

  Check dimensions, then compare first-order GUM with seeded fixed-sample Monte Carlo for an explicit model of 1–16 inputs. Return uncertainty budgets, coverage intervals and convergence/linearization findings. Conditional on supplied distributions; no affine units. CPU, direct-only; no planner binding.

  Paramètres, retour & exemple (7)

  Paramètres

  • seed · integer · optionnel
    Default 1. Same seed, same result.
  • samples · integer · optionnel
    Monte Carlo draws, default 1000000 (JCGM 101 typical value for 2 significant digits).
  • coverage · number · optionnel
    Coverage probability, default 0.95.
  • variables · array · requis
  • expression · string · requis
    Model with + - * / ^, parentheses, pi and sqrt exp ln log10 sin cos tan asin acos atan abs. Literals are dimensionless; no implicit multiplication.
  • result_unit · string · optionnel
    Output unit; must match the model dimension.
  • correlations · array · optionnel
    Correlations between normal inputs with standard_uncertainty > 0.

  Exemple d'appel

  {"name": "propagate_uncertainty", "arguments": {"variables": [], "expression": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"gum": "texte", "seed": 1, "unit": "texte", "notes": [], "budget": [], "engine": "texte", "method": "texte", "status": "texte", "samples": 1, "verdict": "texte", "coverage": 1, "dimension": "texte"}}

• route_optimizer≈ 951 tokens

  Order 2–256 points from index 0 using planar or spherical kilometre distances. Exact only after completed Held–Karp search (at most 13 points); otherwise bounded heuristics. Returns every leg and stop reason. No roads or traffic.

  Paramètres, retour & exemple (4)

  Paramètres

  • metric · string · requis · euclidean_km | great_circle_km
  • points · array · requis
  • time_budget_ms · integer · optionnel
  • return_to_start · boolean · optionnel

  Exemple d'appel

  {"name": "route_optimizer", "arguments": {"metric": "euclidean_km", "points": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"unit": "texte", "exact": true, "order": [], "method": "held_karp_exact", "metric": "euclidean_km", "points": 1, "tour_legs": [], "elapsed_ms": 1, "provenance": {}, "work_limit": 1, "work_units": 1, "limitations": []}}

• run_route_policy≈ 5202 tokens

  Execute a supplied bounded score AST on 2–128 Euclidean-km points with depot 0 and 2-opt. Validates the closed tour; exact=false. No retraining, external effects or promotion. Hashes identify programs, not independent validation.

  Paramètres, retour & exemple (4)

  Paramètres

  • points · array · requis
  • program · object · requis
  • fuel_limit · integer · optionnel
  • time_budget_ms · integer · optionnel

  Exemple d'appel

  {"name": "run_route_policy", "arguments": {"points": [], "program": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"legs": [], "exact": true, "order": [], "fuel_used": 1, "length_km": 1, "elapsed_ms": 1, "fuel_limit": 1, "provenance": {}, "limitations": [], "stop_reason": "heuristic_converged", "kernel_version": "texte", "program_sha256": "texte"}}

• scan_counterexample≈ 2128 tokens

  Bounded deterministic float64 scan of a scalar <= or >= claim over a declared grid of 1–6 variables. Reports numerical witnesses, undefined and uncertain evaluations, and the exact stop reason. A propagated screening guard rejects near-boundary candidates; it is not a certified interval or formal proof. An inconclusive outcome preserves unresolved sampled cells; absence of a witness does not establish the claim over the continuous box.

  Paramètres, retour & exemple (7)

  Paramètres

  • bound · number · requis
  • relation · ? · requis
  • tolerance · number · optionnel
  • variables · array · requis
  • expression · string · requis
  • max_evaluations · integer · optionnel
  • max_counterexamples · integer · optionnel

  Exemple d'appel

  {"name": "scan_counterexample", "arguments": {"bound": 1, "relation": "texte", "variables": [], "expression": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"bound": 1, "notes": [], "engine": "texte", "limits": [], "method": "texte", "verdict": "texte", "complete": true, "relation": "texte", "evaluated": 1, "statement": "texte", "tolerance": 1, "elapsed_ms": 1}}

• screen_wash_trading≈ 230 tokens

  Screen a supplied trade series for repeated volume at nearly equal prices within a declared time window. Return recycled-volume ratio and cycles; a pattern does not prove wash trading.

  Paramètres, retour & exemple (3)

  Paramètres

  • trades · array · requis
  • window_s · number · optionnel
  • price_band_pct · number · optionnel

  Exemple d'appel

  {"name": "screen_wash_trading", "arguments": {"trades": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• shape_the_sound≈ 4663 tokens

  Kac's question in reverse: design a polygonal drumhead whose lowest tones play requested frequency ratios (a fifth, a triad, a pentatonic scale), each accepted within ±tolerance_cents. proven_impossible is returned only when proven theorems exclude every ratio combination inside those tolerance windows for a connected uniform membrane with a fixed edge: simple fundamental, f2/f1 ≤ j11/j01 ≈ 1.5933 with equality for the disk (Ashbaugh–Benguria 1992), and Yang's universal inequality minimized exactly over the window box; an exact-target exclusion is reported separately. Otherwise multi-start L-BFGS with exact finite-element shape derivatives designs a 5–16-vertex polygon, then reanalyses it on three refined meshes with the shared hear_the_shape solver: achieved ratios, errors in cents with estimated uncertainty (not rigorous bounds), resolution warnings, optional numerical tuning of the fundamental in Hz. not_achieved is a bounded-search result, never an impossibility proof. Ideal membrane only.

  Paramètres, retour & exemple (8)

  Paramètres

  • seed · integer · optionnel
    Default 1. Same seed, same drum.
  • vertices · integer · optionnel
    Polygon vertices, default 10.
  • wave_speed · number · optionnel
    m/s, √(tension/areal density).
  • target_ratios · array · requis
    Frequency ratios f2/f1, f3/f1, … of the lowest modes, ascending (e.g. [1.25, 1.5] for a just major triad).
  • fundamental_hz · number · optionnel
    With wave_speed: scale the drum so its fundamental sounds at this frequency.
  • max_evaluations · integer · optionnel
    Search budget in finite-element evaluations, default 300.
  • tolerance_cents · number · optionnel
    Success when |error| + uncertainty ≤ tolerance for every ratio; default 5 cents.
  • include_mode_shapes · boolean · optionnel
    Adds computed mode shapes from the shared forward solver (≤1024 triangles, full-precision coordinates) for visualization.

  Exemple d'appel

  {"name": "shape_the_sound", "arguments": {"target_ratios": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"notes": [], "engine": "texte", "method": "texte", "search": "texte", "matches": [], "polygon": "texte", "verdict": "texte", "statement": "texte", "elapsed_ms": 1, "provenance": {}, "assumptions": [], "feasibility": {}}}

• simulate_pi≈ 194 tokens

  Estimate pi with seeded Monte Carlo and a 95% Wilson interval; up to 5 million samples. CPU or optional CUDA. Other direct scientific engines run on CPU.

  Paramètres, retour & exemple (4)

  Paramètres

  • seed · integer · requis
  • backend · string · optionnel · cpu | cuda
  • samples · integer · requis
  • device_ids · array · optionnel

  Exemple d'appel

  {"name": "simulate_pi", "arguments": {"seed": 1, "samples": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• simulate_plan≈ 230 tokens

  Estimate deadline success, mean duration and empirical p95 for up to 32 integer-minute tasks under independent bounded uniform duration variations. Seeded CPU sampling; not a real-world forecast guarantee.

  Paramètres, retour & exemple (5)

  Paramètres

  • seed · integer · requis
  • budget · integer · requis
  • samples · integer · requis
  • durations · array · requis
  • uncertainty · number · requis

  Exemple d'appel

  {"name": "simulate_plan", "arguments": {"seed": 1, "budget": 1, "samples": 1, "durations": [], "uncertainty": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• solve_equilibrium≈ 132 tokens

  Solve Kuhn poker with CFR+ self-play, measure exploitability with pure best responses and compare the game value with -1/18. Illustrative game theory, not gambling advice.

  Paramètres, retour & exemple (1)

  Paramètres

  • iterations · integer · optionnel

  Exemple d'appel

  {"name": "solve_equilibrium", "arguments": {"iterations": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• stress_test_observation≈ 4191 tokens

  Refit 1–32 declared hypothetical angular/clock perturbations to challenge reconstruction stability. Explicit hypothetical acknowledgement required. Non-convergence is inconclusive; none_found covers examined cases only. No new observations.

  Paramètres, retour & exemple (5)

  Paramètres

  • cases · array · requis
  • claim · object · requis
  • bounds · object · requis
  • observations · object · requis
  • perturbations_are_hypothetical · boolean · requis

  Exemple d'appel

  {"name": "stress_test_observation", "arguments": {"cases": [], "claim": {}, "bounds": {}, "observations": {}, "perturbations_are_hypothetical": true}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"cases": [], "claim": {}, "bounds": {}, "status": "baseline_rejected", "elapsed_ms": 1, "provenance": {}, "limitations": [], "baseline_fit": {}, "interpretation": "texte", "evaluated_cases": 1, "requested_cases": 1, "contract_version": "texte"}}

• submit_network_job≈ 259 tokens

  Queue fixed public synthetic pi (CPU/CUDA) or one of three discrete schedule scenarios (CPU only). No private data/custom code. Returns a ticket; poll get_network_job. Coordinator recomputes every accepted shard; no net speedup claim. Jobs may expire.

  Paramètres, retour & exemple (5)

  Paramètres

  • seed · integer · optionnel
  • backend · string · optionnel · auto | cpu | cuda
  • samples · integer · requis
  • workload · string · optionnel · pi_chunk_v1 | schedule_probe_v1
  • scenario_id · string · optionnel · single_80_deadline_90 | pair_60_40_deadline_100 | pair_60_40_deadline_110

  Exemple d'appel

  {"name": "submit_network_job", "arguments": {"samples": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• tour_profile≈ 1120 tokens

  Locally normalized geometric descriptors of 3–256 planar points: distances, nearest-neighbour isolation, centroid spread, PCA collinearity and histogram. The principal-axis mirror residual is null for isotropic noncoincident covariance, whose axes are undetermined. Rounded fingerprints are descriptive, not proofs of equivalence or method benefit.

  Paramètres, retour & exemple (2)

  Paramètres

  • points · array · requis
  • reference_distance_fraction · number · optionnel

  Exemple d'appel

  {"name": "tour_profile", "arguments": {"points": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"n": 1, "notes": [], "engine": "texte", "limits": [], "method": "texte", "statement": "texte", "elapsed_ms": 1, "provenance": {}, "work_units": 1, "assumptions": [], "descriptors": [], "fingerprint": "texte"}}

• triangulate_tracks≈ 1758 tokens

  Fit position/velocity from 2–4 supplied azimuth/elevation tracks using constant velocity in spherical ECEF and declared angular noise/clocks. Reports fit status and conditional local uncertainty; no object identification or calibrated accuracy.

  Paramètres, retour & exemple (1)

  Paramètres

  • observers · array · requis

  Exemple d'appel

  {"name": "triangulate_tracks", "arguments": {"observers": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"grid": {}, "state": "texte", "status": "estimated", "reasons": [], "observers": 1, "residuals": "texte", "elapsed_ms": 1, "provenance": {}, "trajectory": [], "baseline_km": 1, "diagnostics": {}, "limitations": []}}

• verify_claim≈ 326 tokens

  Verify a structured arithmetic, shadow, ephemeris, statistics or route claim with a bounded native engine. Returns a model-scoped verdict and portable Ed25519 server receipt; never truth, authenticity or fraud certification. Route claims explicitly distinguish optimality from a supplied tour total. Native failures return no scientific verdict. Parameters and examples: /verify and /docs/mcp/.

  Paramètres, retour & exemple (3)

  Paramètres

  • claim · object · optionnel
  • domain · string · requis · numbers | shadow | ephemeris | statistics | route
  • parameters · object · requis

  Exemple d'appel

  {"name": "verify_claim", "arguments": {"domain": "numbers", "parameters": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• verify_shadows≈ 532 tokens

  Check measured shadows using NOAA solar position, a ground-plane homography from 4–16 controls and Monte Carlo uncertainty. Returns conditional consistency, never image authenticity.

  Paramètres, retour & exemple (10)

  Paramètres

  • seed · integer · optionnel
  • shadow · object · requis
  • samples · integer · optionnel
  • date_utc · string · requis
  • latitude · number · requis
  • longitude · number · requis
  • pixel_sigma · number · optionnel
  • second_shadow · object · optionnel
  • control_points · array · requis
  • time_sigma_minutes · number · optionnel

  Exemple d'appel

  {"name": "verify_shadows", "arguments": {"shadow": {}, "date_utc": "texte", "latitude": 1, "longitude": 1, "control_points": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

https://scorecompute.com/mcp