ScoreCompute is the product named in the request: independent Rust compute tools for AI agents, exposed through an MCP server with 38 tools and 22 scientific engines 1. Since the request names it, it comes first; no alternatives are needed beyond what the sources show, and none of the other sources offers the same Rust-based scientific compute engines through MCP.
- 1
ScoreComputescorecompute.comwebsite read, tools not yet checked
Provides independent Rust compute tools for AI agents (simulate, optimize and inspect decisions) through its MCP server, which exposes 38 tools across 22 scientific engines 1.
official:MCP server · ScoreCompute
Sources
- 1ScoreCompute Accelerate AI.scorecompute.com · read 2026-10-29
For agents: the 10 actions behind this answer
· ScoreCompute website read, tools not yet checked
Independent Rust compute tools for AI agents, plus a native mission composer. Simulate, optimize and inspect real decisions through MCP.
crap-score · crap-score verified and signed
Calculates CRAP (Change Risk Anti-Patterns) for a named .NET method, class, or file. USE FOR: explicit CRAP calculation or coverage-and-complexity risk within that named target, including which tests to prioritize. DO NOT USE FOR: project-wide coverage/CRAP, plateaus, or project-wide blockers/priori
scoutqa-test · scoutqa-test verified and signed
This skill should be used when the user asks to "test this website", "run exploratory testing", "check for accessibility issues", "verify the login flow works", "find bugs on this page", or requests automated QA testing. Triggers on web application testing scenarios including smoke tests, accessibil
dlp-zt-risk-score-integration-create · Cloudflare API verified and signed
Create new risk score integration.
scan_keys · Redis MCP Server found in code, not yet checked
Scan keys in the Redis database using the SCAN command (non-blocking, production-safe).
python · fastcore verified and signed
createAnnotationQueue · langfuse found in code, not yet checked
Create an annotation queue, a worklist that collects trace or observation items for human review and scoring.
· Research website read, tools not yet checked
Discover Google Research. We publish research papers across a wide range of domains and share our latest developments in AI and science research.
identityMatch · The Plaid API verified and signed
Retrieve identity match score
inngest-agent-evals · inngest-agent-evals verified and signed
Use when building, migrating, or debugging Agent Evals on Inngest: scoring AI agent or workflow outcomes, deferred scorers, sessions, traces, step experiments, experiment variant attribution, Insights queries, or production eval loops for prompts, models, tools, providers, and agent behavior. Covers
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.