- Autario @autario/autario-mcpQuery 8,000+ verified open datasets (World Bank, Eurostat, FRED, SEC) with stats and charts.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Predictalot @psyb0t/predictalotSelf-hosted MCP server for time-series forecasting and tabular ML via foundation models.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.2 GitHub stars.
- Clinical Trial Design @wei-ai-lab/clinical-trial-designPhase 2/3 clinical trial design via gsDesign / gsDesign2: sample size, GS boundaries, multiplicity3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Jaeger @mshegolev/jaeger-mcpJaeger MCP — search traces, inspect spans, map service dependencies (read-only).4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.2 GitHub stars.
- Stathead @dachhack/stathead-mcpFantasy football analytics: stats, dynasty, projections, prospects, Sleeper leagues, Excel I/O3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Academic Research Kernel @xngg1021/academic-research-kernelDeterministic research state, evidence validation and statistical recomputation.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- dYdX Agent Gateway @alekskram/dydx-agent-gatewayAnalytics-only MCP gateway to dYdX v4: auditable trader PnL, funding and OI detectors. No keys.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Ephys @happyc0der/ephys-mcpRead-only analysis of intracortical BCI recordings (NWB, DANDI, WAV): spikes, PSTHs, decoding, plots3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Rigor @mrnh/rigor-mcpVerified statistical inference for AI agents: hypothesis tests, sequential testing, power.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- IPCC AR6 Climate Retrieval @aswanisahoo/climate-ipcc-ragSearch IPCC AR6 WG1 and answer with page-level citations, or refuse when unsupported.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.1 GitHub stars.
- Golf Coach @bjornj12/golf-coachA stats-driven golf coach: Trackman + on-course rounds, turned into a practice plan.16% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Engageable Analytics @engageable/analyticsUnified analytics MCP server for GA4, Mixpanel, and PostHog.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- MCP Pirsch @verygoodplugins/mcp-pirschPirsch Analytics with natural language queries and trend analysis4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Log @rog0x/logLog parse, filter, analyze for AI agents5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Semantic Frame @anarkitty1/semantic-frameToken-efficient semantic compression for numerical data. 95%+ token reduction.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- glin @akashchatterjee/glinExactly explainable classifiers for agents: train, tune, predict, explain on CSV or Excel.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Dataset Explorer @khanarmaghanrasheed-18/dataset-explorerLocal MCP analysis for CSV, TSV, Excel, JSON and Parquet: summaries, outliers and relationships.Not assessed yet.Runs on your machine, installed from PyPI.
- Calibration Explorer @m-sanchez/calibration-explorerCheck classifier confidence against accuracy, fit temperature scaling and save local reports.Not assessed yet.Runs on your machine, installed from npm.
- 竞品内容 Pattern 雷达 · AI 答案里的重复说法 @savantcat/pattern-radar把 AI 答案/竞品内容当语料，找出反复出现的说法、被反复引用的信源与答案同质化程度，含对照组自检3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.
- NHANES (design-correct survey analysis) @blackswancausallabs/nhanes-mcpDesign-correct NHANES analysis: survey weights, pooled cycles, CIs and NCHS reliability flags.2% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- HN Hiring Trends @alialtunar/hn-hiring-trends-mcpSkill demand trends, salaries and job search from Hacker News Who is hiring threads. No API keys.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Skill Stats Reporter @dailyaiagents-cpu/skill-stats-reporterReads data/skill-telemetry/invocations.jsonl and produces daily stats — dead skills (zero invocat...12% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.
- Police Transparency @mrfentmen/police-transparency-mcpUse this MCP server to Aggregate historical NYC police complaint statistics with no person...4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Rechtssysteem.ai @rechtssysteem/rechtssysteem-mcpLekkage-vrije voorspelling van Nederlandse rechtszaken, getraind op 609.715 uitspraken9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.
