Connect

8 clients · secrets stay placeholders

JSON (mcpServers)Claude CodeCodexOpenCodeCursorVS CodeGemini CLIGoose

{
  "mcpServers": {
    "scorecompute": {
      "type": "http",
      "url": "https://scorecompute.com/mcp"
    }
  }
}

claude mcp add --transport http scorecompute https://scorecompute.com/mcp

[mcp_servers.scorecompute]
url = "https://scorecompute.com/mcp"

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "scorecompute": {
      "type": "remote",
      "url": "https://scorecompute.com/mcp",
      "enabled": true
    }
  }
}

{
  "mcpServers": {
    "scorecompute": {
      "type": "http",
      "url": "https://scorecompute.com/mcp"
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=scorecompute&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vc2NvcmVjb21wdXRlLmNvbS9tY3AifQ%3D%3D"
}

{
  "servers": {
    "scorecompute": {
      "type": "http",
      "url": "https://scorecompute.com/mcp"
    }
  }
}

{
  "mcpServers": {
    "scorecompute": {
      "httpUrl": "https://scorecompute.com/mcp"
    }
  }
}

extensions:
  "scorecompute":
    enabled: true
    name: "scorecompute"
    type: streamable_http
    uri: "https://scorecompute.com/mcp"
    timeout: 300

Quality 72 / 100needs work

protocol75 · weight 25

warn
protocol.modernnewest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
n/a
protocol.statelessonly applies to 2026-07-28 servers
pass
protocol.transportstreamable HTTP
n/a
protocol.list_ttlonly applies to 2026-07-28 servers

authorizationn/a · weight 15

n/a
auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
n/a
auth.secret_in_urlno templated URL

tool hygiene93 · weight 30

pass
tools.descriptionsevery tool has a description
pass
tools.description_lengthdescriptions are concise
pass
tools.schemasevery tool has an object input schema
pass
tools.annotations38 of 38 tools declare readOnlyHint or destructiveHint
pass
tools.directory_hintsevery tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
warn
tools.token_costabout 16,740 tokens to load every tool
pass
tools.api_dumptools are not a one-to-one API dump

stability25 · weight 15

warn
stability.changes65 tool changes in 30 days
fail
stability.rug_pull23 tools kept their name but changed most of their description in 30 days; review before trusting them

dependenciesn/a · weight 15

n/a
deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

38 tools, about 16,740 tokens to load them all · tool set 00e11ffd8b89 · tools last changed 2026-10-05 · checked 2026-10-19 21:10 UTC

Tool changes

2026-10-05tour_profileadded
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.
2026-10-05scan_counterexampleadded
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.
2026-10-04shape_the_soundadded
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.
2026-10-02verify_claimadded
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/.
2026-10-02check_arithmeticadded
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.
2026-10-01propagate_uncertaintyadded
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.
2026-10-01kepler_stabilityadded
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.
2026-10-01hear_the_shapeadded
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.
2026-10-01compute_orbitchangeddescription, input schema, output schema
before
Compute an ideal elliptical orbit around one solar mass. Time is measured from periapsis and distances are in astronomical units. This two-body model is not a real celestial ephemeris.
after · 61% of words in common
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.
2026-10-01get_network_jobchangeddescriptionmeaning changed
before
Read one public contributor ticket and verified progress. Completed pi jobs contain estimate; completed schedule jobs have estimate/inside null and report successes, probability and a fixed-sample Wilson95 interval under the declared discrete synthetic model. A model probability does not establish real completion. Worker-reported elapsed time, coordinator verification time and total wall time remain separate. Each shard counts once; expired or duplicate results are rejected. No private user data is accepted.
after · 35% of words in common
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.

Showing the latest 10. Full history: list_changes · trend: quality JSON.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.

Trust 82 / 100

no-repository

provenance55

liveness98

freshness100

hygiene80

+dns-namespace +website +reachable +uptime-96% +updated-13d-ago -no-repository

Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.

Endpoints

remote	auth	reachable	uptime 30d	p50	protocol	last ok
`https://scorecompute.com/mcp` streamable-http	none	yes	96%	576 ms	2025-11-25	2026-10-19

Tools (38)

`analyze_chess_game`read-only	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.
`analyze_kinematics`read-only	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.
`assimilate_observation`read-only	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.
`audit_statistics`read-only	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.
`build_robust_plan`read-only	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.
`check_arithmetic`read-only	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.
`check_ephemeris`read-only	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.
`check_shadow_track`read-only	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.
`compose_capabilities`read-only	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.
`compute_orbit`read-only	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.
`execute_composition`read-only	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.
`forge_route_policy`read-only	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.
`get_network_job`read-only	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.
`hear_the_shape`read-only	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.
`improve_schedule`read-only	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.
`kepler_stability`read-only	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.
`list_capabilities`read-only	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.
`list_composition_capabilities`read-only	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-only	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`read-only	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.
`plan_golden_hour`read-only	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.
`plan_mission`read-only	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.
`plan_observation`read-only	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.
`propagate_uncertainty`read-only	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.
`route_optimizer`read-only	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.
`run_route_policy`read-only	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`read-only	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.
`screen_wash_trading`read-only	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.
`shape_the_sound`read-only	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.
`simulate_pi`read-only	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.
`simulate_plan`read-only	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.
`solve_equilibrium`read-only	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.
`stress_test_observation`read-only	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.
`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 may expire.
`tour_profile`read-only	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.
`triangulate_tracks`read-only	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.
`verify_claim`read-only	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/.
`verify_shadows`read-only	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.

Schemas: list_tools.

Similar MCP servers

Official server.json

{
  "name": "com.scorecompute/scorecompute",
  "_meta": {
    "io.modelcontextprotocol.registry/publisher-provided": {
      "tags": [
        "rust",
        "cuda",
        "monte-carlo",
        "optimization",
        "astronomy",
        "solar-shadows",
        "statistical-audit",
        "mcp",
        "native-orchestration",
        "robust-scheduling",
        "typed-composition",
        "capability-planning",
        "geometric-routing",
        "route-risk",
        "distributed-computing",
        "volunteer-computing",
        "observation-design",
        "conditional-uncertainty",
        "counterexample-search",
        "data-assimilation",
        "schedule-improvement",
        "golden-hour",
        "claim-verification",
        "exact-arithmetic",
        "signed-receipts"
      ],
      "limits": {
        "maxRequestBytes": 1048576,
        "maxSessionsTotal": 64,
        "sessionIdleMinutes": 15,
        "maxSessionsPerAddress": 8,
        "maxConcurrentRustCalculations": 1
      },
      "privacy": "The bounded public in-memory feed displays declared client name/version, tool, status and duration; identity is not authenticated. Operational aggregate metrics store no addresses, identities, inputs, results or Verify receipts. Retention: daily aggregates 90 UTC days; availability seven days; optional pricing email/plan/consent 30 days; private suggestions 90 days. No payment or marketing message is triggered. Contributor state, hosting/security logs and backups have separate rules at /privacy/. Never put secrets in clientInfo.",
      "summary": "38 independently callable MCP tools: 22 Rust scientific, six Discovery, six optional composition, three network and one Verify tool. Verify checks arithmetic, shadows, ephemerides, statistics and geometric routes, with model-scoped Ed25519 receipts; signatures do not establish physical truth or independent certification. Optimality claims differ from supplied-tour totals. Exact arithmetic uses checked rationals; unsupported floating-point paths remain inconclusive. tour_profile returns deterministic geometry descriptors only and promotes no method; scan_counterexample performs a bounded fixed-order grid scan with unresolved numerical cells explicit; absence on sampled cells is never a proof. Method Lab is bounded, train-only and never automatically promotes methods. Observation forecasts are conditional. Direct engines need no orchestrator. The typed bank has 22 capabilities and 46 fact contracts. CUDA supports simulate_pi and pi_chunk_v1. Contributor jobs are recomputed by the coordinator; no net distributed speedup is claimed.",
      "gpuTools": [
        "simulate_pi"
      ],
      "retention": {
        "privacyUrl": "https://scorecompute.com/privacy/",
        "pricingInterestDays": 30,
        "visitorSuggestionDays": 90,
        "availabilityHistoryDays": 7,
        "dailyAggregateUsageDays": 90,
        "verifyReceiptServerStorage": false,
        "scientificInputResultMetricsStorage": false
      },
      "toolNames": [
        "simulate_pi",
        "optimize_tasks",
        "compute_orbit",
        "verify_shadows",
        "check_ephemeris",
        "audit_statistics",
        "analyze_kinematics",
        "check_shadow_track",
        "solve_equilibrium",
        "analyze_chess_game",
        "screen_wash_trading",
        "simulate_plan",
        "route_optimizer",
        "triangulate_tracks",
        "plan_observation",
        "stress_test_observation",
        "assimilate_observation",
        "improve_schedule",
        "list_capabilities",
        "plan_mission",
        "build_robust_plan",
        "list_composition_capabilities",
        "compose_capabilities",
        "execute_composition",
        "network_status",
        "submit_network_job",
        "get_network_job",
        "plan_golden_hour",
        "forge_route_policy",
        "run_route_policy",
        "hear_the_shape",
        "shape_the_sound",
        "propagate_uncertainty",
        "kepler_stability",
        "check_arithmetic",
        "verify_claim",
        "tour_profile",
        "scan_counterexample"
      ],
      "categories": [
        "Scientific computing",
        "Statistics",
        "Optimization",
        "Astronomy",
        "Physical consistency"
      ],
      "toolCounts": {
        "total": 38,
        "discovery": 6,
        "scientific": 22,
        "composition": 6,
        "verification": 1,
        "contributorNetwork": 3
      },
      "availability": "Public service backed by a connected compute worker. Calculations can be temporarily unavailable when that machine or its connection is offline. The separate contributor network depends on opted-in clients and exposes queued/expired states.",
      "documentation": {
        "trust": "https://scorecompute.com/trust/",
        "status": "https://scorecompute.com/status/",
        "verify": "https://scorecompute.com/verify/",
        "connect": "https://scorecompute.com/connect/",
        "pricing": "https://scorecompute.com/pricing/"
      },
      "authentication": "No API key required for rate-limited public access."
    }
  },
  "icons": [
    {
      "src": "https://scorecompute.com/favicon.svg",
      "mimeType": "image/svg+xml"
    }
  ],
  "title": "ScoreCompute",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://scorecompute.com/mcp",
      "type": "streamable-http"
    }
  ],
  "version": "0.17.1",
  "websiteUrl": "https://scorecompute.com/",
  "description": "38 MCP tools: Rust computation, Discovery, composition, counterexample scans and signed checks."
}