Connect ScoreCompute and your agent gets 38 tools, among them analyze_chess_game, analyze_kinematics, assimilate_observation. It answers at https://scorecompute.com/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 4 of 4 times since 30 September 2026; the last check, on 16 November 2026, succeeded.
38 MCP tools: Rust computation, Discovery, composition, counterexample scans and signed checks.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
analyze_chess_game | 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. Inputs: positions, depth |
analyze_kinematics | 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. Inputs: angular_speed_deg_per_s, distance_min_km, distance_max_km, claimed_distance_km, claimed_speed_kmh |
assimilate_observation | 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. Inputs: observations, new_series, objective, assumptions, data_origin |
audit_statistics | 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. Inputs: n, mean, sd, decimals, min_value, max_value |
build_robust_plan | 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. Inputs: items, budget, uncertainty, min_success_rate, samples, seed |
check_arithmetic | 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 Inputs: claimed_value, expression, tolerance_absolute, tolerance_relative, values |
check_ephemeris | 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. Inputs: date_utc, latitude, longitude, object, claimed_azimuth_deg, claimed_elevation_deg |
check_shadow_track | 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. Inputs: date_utc, latitude, longitude, samples, tolerance_deg |
compose_capabilities | 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 argum Inputs: goals, available, constraints, inputs, adapters |
compute_orbit | 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. Inputs: eccentricity, elapsed_days, semi_major_au |
execute_composition | 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 a Inputs: goals, available, constraints, inputs, adapters |
forge_route_policy | 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 validat Inputs: train, seed, budget |
get_network_job | 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 guaran Inputs: job_id |
hear_the_shape | 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 isospectrali Inputs: boundary, compare_polygon, include_mode_shapes, modes, polygon, wave_speed |
improve_schedule | 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 deli Inputs: items, required_indices, deadline_minutes, extra_minutes, removal_sets, costs |
kepler_stability | 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 Inputs: a_max_au, a_min_au, duration_yr, e_max, e_min, initial_phase_deg |
list_capabilities | 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. Inputs: theme |
list_composition_capabilities | 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. |
network_status | 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. |
optimize_tasks | 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. Inputs: budget, items |
plan_golden_hour | 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 cove Inputs: date_utc, latitude, longitude |
plan_mission | 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. Inputs: items, budget, uncertainty, min_success_rate, samples, seed |
plan_observation | 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. Pred Inputs: observations, candidates, objective, constraints, assumptions |
propagate_uncertainty | 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 distrib Inputs: correlations, coverage, expression, result_unit, samples, seed |
route_optimizer | 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. Inputs: metric, points, return_to_start, time_budget_ms |
run_route_policy | 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. |
scan_counterexample | 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-boun Inputs: bound, expression, max_counterexamples, max_evaluations, relation, tolerance |
screen_wash_trading | 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. Inputs: trades, window_s, price_band_pct |
shape_the_sound | 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 Inputs: fundamental_hz, include_mode_shapes, max_evaluations, seed, target_ratios, tolerance_cents |
simulate_pi | 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. Inputs: samples, seed, backend, device_ids |
simulate_plan | 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. Inputs: durations, budget, samples, seed, uncertainty |
solve_equilibrium | 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. Inputs: iterations |
stress_test_observation | 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. Inputs: observations, claim, bounds, cases, perturbations_are_hypothetical |
submit_network_job | 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 Inputs: samples, seed, backend, workload, scenario_id |
tour_profile | 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, who Inputs: points, reference_distance_fraction |
triangulate_tracks | 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 accur Inputs: observers |
verify_claim | 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 ex Inputs: domain, parameters, claim |
verify_shadows | 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. Inputs: date_utc, latitude, longitude, control_points, shadow, second_shadow |
Every block below points at https://scorecompute.com/mcp. Pick your client and copy.
claude mcp add --transport http scorecompute https://scorecompute.com/mcp
{
"mcpServers": {
"scorecompute": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://scorecompute.com/mcp"]
}
}
}{
"mcpServers": {
"scorecompute": {
"url": "https://scorecompute.com/mcp"
}
}
}{
"servers": {
"scorecompute": {
"type": "http",
"url": "https://scorecompute.com/mcp"
}
}
}{
"context_servers": {
"scorecompute": {
"url": "https://scorecompute.com/mcp"
}
}
}{
"mcpServers": {
"scorecompute": {
"serverUrl": "https://scorecompute.com/mcp"
}
}
}{
"mcpServers": {
"scorecompute": {
"url": "https://scorecompute.com/mcp"
}
}
}name: ScoreCompute
version: 0.0.1
schema: v1
mcpServers:
- name: ScoreCompute
type: streamable-http
url: https://scorecompute.com/mcp{
"mcpServers": {
"scorecompute": {
"httpUrl": "https://scorecompute.com/mcp"
}
}
}{
"mcpServers": {
"scorecompute": {
"type": "http",
"url": "https://scorecompute.com/mcp"
}
}
}{
"mcpServers": {
"scorecompute": {
"url": "https://scorecompute.com/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fscorecompute.com%2Fmcp&type=streamable_http&id=scorecompute&name=ScoreCompute
It answered our last check on 16 November 2026 in 124 ms. Over 4 checks since 30 September 2026 it answered 4. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by scorecompute.com and served from scorecompute.com, the vendor's own domain: https://scorecompute.com/mcp.
38, as returned by the server's own tools/list on 18 November 2026: analyze_chess_game, analyze_kinematics, assimilate_observation, audit_statistics, build_robust_plan, check_arithmetic, check_ephemeris, check_shadow_track, and 30 more.
It answered our last check on 16 November 2026 in 124 ms. Over 4 checks since 30 September 2026 it answered 4.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://scorecompute.com/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: com.scorecompute. Endpoint host: scorecompute.com. ARD identifier: urn:air:com.scorecompute:mcp:scorecompute.
First indexed 30 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.