# ScoreCompute

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

- name: com.scorecompute/scorecompute
- version: 0.17.1
- connection class: R0 (autonomous)
- trust: 82/100 flags: no-repository
- quality: 72/100 (needs work)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/com.scorecompute%2Fscorecompute
- tools: https://api.protogrid.dev/v1/servers/com.scorecompute%2Fscorecompute/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

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


## Trust

- hygiene: 80
- liveness: 98
- freshness: 100
- provenance: 55
- drivers: +dns-namespace +website +reachable +uptime-96% +updated-14d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 72/100 (needs work)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 93 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 38 of 38 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- warn `tools.token_cost`: about 16,740 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 25 (weight 15)

- warn `stability.changes`: 65 tool changes in 30 days
- fail `stability.rug_pull`: 23 tools kept their name but changed most of their description in 30 days; review before trusting them

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 38, about 16,740 tokens to load them all
- tool set hash: 00e11ffd8b897d835feca6f3f51a2cb7
- tools last changed: 2026-10-05T03:14:34.520Z
- badge: [![protogrid quality](https://protogrid.dev/badge/com.scorecompute/scorecompute.svg)](https://protogrid.dev/servers/com.scorecompute/scorecompute)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-05 `tour_profile` added
  - 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.
- 2026-10-05 `scan_counterexample` added
  - 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.
- 2026-10-04 `shape_the_sound` added
  - 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.
- 2026-10-02 `verify_claim` added
  - 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/.
- 2026-10-02 `check_arithmetic` added
  - 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.
- 2026-10-01 `propagate_uncertainty` added
  - 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.
- 2026-10-01 `kepler_stability` added
  - 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.
- 2026-10-01 `hear_the_shape` added
  - 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.
- 2026-10-01 `compute_orbit` changed (description, inputSchema, outputSchema)
  - 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: 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.
- 2026-10-01 `get_network_job` changed (description) **meaning 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: 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.

Full history: https://api.protogrid.dev/v1/servers/com.scorecompute%2Fscorecompute/changes

## Remotes

- https://scorecompute.com/mcp (streamable-http, auth none, reachable true, uptime30d 0.96153843)

## Packages

_none_

## Tools (38)

- `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.
- `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.
- `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.
- `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.
- `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.
- `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 integrity digest; no checks of units or model meaning.
- `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.
- `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.
- `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 arguments.
- `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.
- `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 advertised bindings.
- `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 validation, arbitrary code or automatic promotion.
- `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 guarantees.
- `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 isospectrality; no damping. CPU, direct-only; no planner binding.
- `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 delivery reliability.
- `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; radial overlap is not an encounter. Direct-only.
- `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.
- `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.
- `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 covers reference dates only. Shared solar models are not independent corroboration.
- `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.
- `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. Prediction is not an acquired measurement or visibility proof.
- `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 distributions; no affine units. CPU, direct-only; no planner binding.
- `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.
- `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-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`: 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`: 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`: 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`: 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`: 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`: 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`: 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`: 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`: 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`: 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.