Explore
MCP servers and skills: search, filter by where they run, and compare.
ml-workflow-skillflying-pelican
HostedMakes AI agents iterate on ML models keeping the human user in the loop
SkillLink only★ 2Few stars
ml-paper-humanizerFwibo
Local
MCP servers and skills: search, filter by where they run, and compare.
Makes AI agents iterate on ML models keeping the human user in the loop
SkillLink only★ 2Few stars
Claude Code / Codex skill that removes the AI smell from ML conference paper prose: reads like a person wrote it, not an AI. 给 ML 论文去 AI 味。
SkillMIT★ 3Few starsNo key
Claude skills for ML: turn research papers into clear breakdowns and minimal, runnable PyTorch code
SkillMIT★ 1Few starsNo key
BigQuery ML, BigQuery AI, and 4-Lens Agent Skills: 104 live-verified SQL/Python workflows, zero-dependency CLI catalog & skill installer, and stdio MCP server.
PythonApache-2.0Few starsNo key
Hybrid post-quantum cryptography for TypeScript and JavaScript (ML-KEM, ML-DSA, SLH-DSA). Rust compiled to WebAssembly.
Node.jsApache-2.0★ 1Few starsNo key
An evidence-grounded agent skill for Artificial Intelligence (AI), Machine Learning (ML), and Scientific Machine Learning (SciML) paper review.
SkillMITFew starsNo key
Verify post-quantum (ML-DSA-65 / NIST FIPS 204) signatures and buy proof, provenance and AI-decision receipts over x402 (USDC on Base). MCP server. Public source mirror of the npm package. Not a FIPS-
Node.jsMITFew starsNo key
🧛 Post-quantum blockchain: ML-DSA everywhere, passkey wallets, .boo names, and an MCP server so agents can use it from one prompt
SkillMIT★ 2Few starsNo key
SkillMIT★ 1Few starsNo key
PythonMIT★ 1Few starsNo key
Post-quantum (ML-DSA-65 / NIST FIPS 204) AI-agent identity + signed AI-decision receipts, verifiable offline. MCP server with 2 free and 9 x402-paid tools (USDC on Base). Not a FIPS-validated CMVP mod
Node.jsMITFew starsNo key
Post-quantum envelopes for files, messages and agents. Hybrid ML-KEM-768 + X25519, ML-DSA-65 signatures, MCP-native.
Node.jsMITFew starsNo key
AegisGate MCP — Standalone Model Context Protocol security server with 23 security layers, vendored ONNX runtime, neural threat detection (L3). SSE streaming. Session management. Zero module dependenc
DockerApache-2.0Few starsNo key
Python toolkit for financial machine learning, implementing methods from López de Prado’s Advances in Financial Machine Learning: purged cross-validation, triple-barrier labels, fractional differentia
PythonMIT★ 2Few starsNo key
Agent-driven ML researcher in a secure, reproducible KVM lab: five standalone scientific-state MCP servers within per-user VMs with driver / trusted / hostile zone isolation
SkillApache-2.0★ 7No key
Claude Code subagents and campaigns that audit ML and geoscience pipelines (provenance, spatial leakage, seeds, baselines, physics, statistics) before results become claims.
SkillMIT★ 1Few starsNo key
Atlas United storm data API: ML Storm Forecast by Address, Model-Based Weather and Hourly Forecast by Address, Storm History by Address since 2003, Past Storm Leads by Address. Pay per address, x402,
Hosted by authorMITFew starsNo key
Claude Code skills for engineering, research, and patent work where a plausible answer isn't good enough. Built-in checks for trade-offs, failure modes, prior art, and weak claims
SkillMIT★ 1Few starsNo key
Twelve Claude skills built from real failures — knowledge retrieval, session handoff, ML notebook workflow, and small guardrails.
SkillMITFew starsNo key
How much water and energy does AI use? MCP server and JSON API for the water and energy footprint of AI, with boundary, assumptions and sources attached.
Hosted by authorMIT★ 1Few starsNo key
Self-hosted AI platform on Kubernetes (k3s) for AI agents, RAG and MLOps: MCP tool servers, LangGraph, LiteLLM model routing with an evaluation gate, MLflow, Dagster and BentoML, OpenTelemetry tracing
SkillMIT★ 9No key
Find data leakage in ML code before your metrics lie to you. Static analyzer + agent skill + Claude Code hook.
SkillMITFew starsNo key
Who stands behind it
