Agents Index

ScoreCompute

Online

38 MCP tools: Rust computation, Discovery, composition, counterexample scans and signed checks.

Visit publisherConnectJSON

What it can do: 38 tools

  • simulate_pi read-onlyEstimate 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.
  • optimize_tasks read-onlyExactly 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.
  • verify_shadows read-onlyCheck measured shadows using NOAA solar position, a ground-plane homography from 4–16 controls and Monte Carlo uncertainty. Returns conditional consistency, never image authenticity.
  • check_ephemeris read-onlyCheck 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.
  • audit_statistics read-onlyApply 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.
  • analyze_kinematics read-onlyConvert 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.
  • check_shadow_track read-onlyCompare 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.
  • solve_equilibrium read-onlySolve 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.
  • analyze_chess_game read-onlyCompare 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.
  • screen_wash_trading read-onlyScreen 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.
  • simulate_plan read-onlyEstimate 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.
  • route_optimizer read-onlyOrder 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
  • forge_route_policy read-onlyTrain 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.
  • run_route_policy read-onlyExecute 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 va
  • plan_golden_hour read-onlyCompute 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; or
  • triangulate_tracks read-onlyFit 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
  • plan_observation read-onlyFit 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
  • assimilate_observation read-onlyRefit 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 ac
  • stress_test_observation read-onlyRefit 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.
  • improve_schedule read-onlyCompare 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
  • list_capabilities read-onlyRead 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.
  • plan_mission read-onlyPreview 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
  • build_robust_plan read-onlyCompare 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 nati
  • list_composition_capabilities read-onlyRead 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.
  • compose_capabilities read-onlyPlan 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; execu
  • execute_composition read-onlyRun 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 saf
  • network_status read-onlyRead 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.
  • submit_network_jobQueue 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
  • get_network_job read-onlyRead 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
  • check_arithmetic read-onlyCheck 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. I
  • compute_orbit read-onlyCompute 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.
  • hear_the_shape read-onlyCompute 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 no
  • kepler_stability read-onlySurvey 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 prov
  • propagate_uncertainty read-onlyCheck 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
  • scan_counterexample read-onlyBounded 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 gua
  • shape_the_sound read-onlyKac'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
  • tour_profile read-onlyLocally 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 noncoinci
  • verify_claim read-onlyVerify 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 certificat

Connect it

Claude Code
claude mcp add --transport http scorecompute https://scorecompute.com/mcp
Claude.ai / ChatGPT
Settings → Connectors → Add custom connector
URL: https://scorecompute.com/mcp
Cursor (~/.cursor/mcp.json)
{
  "mcpServers": {
    "scorecompute": {
      "url": "https://scorecompute.com/mcp"
    }
  }
}
VS Code (.vscode/mcp.json)
{
  "servers": {
    "scorecompute": {
      "type": "http",
      "url": "https://scorecompute.com/mcp"
    }
  }
}

Questions

What does ScoreCompute do?

38 MCP tools: Rust computation, Discovery, composition, counterexample scans and signed checks. It exposes 38 tools to AI assistants.

What tools does ScoreCompute provide?

38 tools, including simulate_pi, optimize_tasks, verify_shadows, check_ephemeris, audit_statistics, analyze_kinematics, check_shadow_track, solve_equilibrium, analyze_chess_game, screen_wash_trading, simulate_plan, route_optimizer….

How do I connect ScoreCompute to Claude, ChatGPT or Cursor?

Add the remote MCP endpoint https://scorecompute.com/mcp as a custom connector or MCP server. Copy-paste setup is on this page.

Does ScoreCompute require an account or API key?

No sign-in was needed to list its tools. Individual tools may still need an account or API key.

Is ScoreCompute online?

As of 2026-11-19 our probe found it online. It answered 100% of our last 3 checks.

Who publishes ScoreCompute?

scorecompute.com. The official MCP Registry verified that the publisher controls this domain before accepting the listing.

Similar in Travel, Maps & Places