Statistics MCP servers

A server here statistical analysis: descriptive statistics, hypothesis tests, regression, forecasting.

Not here: serving published statistics tables.

369servers
194 remote175 localTagged by Odel's AI, which can make mistakes
By GitHub stars, at most two per publisher
  1. Number 1: AutoTS@winedarksea/autotsAutomated time series forecasting with model search, anomaly detection, and event risk analysis3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1,430 GitHub stars.
  2. Number 2: Kronos@hangeaiagent/kronos-mcpStock price forecasting for China A-shares — Kronos K-line time-series model8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.573 GitHub stars.
  3. Number 3: Bagel@extelligence-ai/bagelPlain-English analysis of robotics, drone, and IoT data, with intelligent edge data reduction.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.397 GitHub stars.

Best fit

155 made for this, ranked by starsRemoteLocal
  1. ClaudeR - RStudio MCP Server @imnmv/clauderConnect RStudio to AI assistants for interactive R coding and data analysis.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.350 GitHub stars.
  2. Stata @sepinetam/stata-mcpLet LLM help you achieve your regression analysis with Stata6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.263 GitHub stars.
  3. tsbootstrap @astrogilda/tsbootstrapRead-only time-series bootstrap server: diagnose a series and compute confidence intervals.2% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.95 GitHub stars.
  4. SAS Viya @sassoftware/sas-mcp-serverExecute SAS code and query Compute, CAS, and model APIs on SAS Viya via OAuth 2.0.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.64 GitHub stars.
  5. ChatSpatial @cafferychen777/chatspatialSchema-enforced spatial transcriptomics analysis with 20 tools and 65 methods via MCP4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.44 GitHub stars.
  6. VARRD — Statistically Validated Trading Edges + AI Research Engine @augiemazza/varrdValidated trading edges across futures, equities, crypto. Live signals, full audit trail.13% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.24 GitHub stars.
  7. Stats Compass @oogunbiyi21/stats-compass50+ pandas-powered tools for data loading, cleaning, visualization, and ML workflows7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.17 GitHub stars.
  8. Oraclaw @whatsonyourmind/oraclawDecision intelligence MCP — 17 tools (optimize, simulate, predict, score, graph). Sub-25ms.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.13 GitHub stars.
  9. Quantoracle @fel123/quantoracle73 deterministic quant tools for AI agents. LLMs drift on Black-Scholes; these are exact math.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.12 GitHub stars.
  10. AutoCarver @mdefrance/autocarverQualify dataset columns and process them against a target with AutoCarver, fully on your machine.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.11 GitHub stars.
  11. Lumino MCP Server @geored/luminoAI-powered SRE observability for Kubernetes/OpenShift with 40+ Tekton debugging tools5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.11 GitHub stars.
  12. Vmanomaly @victoriametrics-community/mcp-vmanomalyMCP Server for vmanomaly - VictoriaMetrics anomaly detection3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.10 GitHub stars.
  13. SportIQ @ninjabeam20/sportiq-mcpMCP tools for FIFA World Cup 2026 football, Formula 1, and IPL cricket — sims, strategy, fantasy.3% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.10 GitHub stars.
  14. QuantContext @zomma-dev/quantcontextDeterministic stock screening, backtesting, and factor analysis for AI trading agents4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.9 GitHub stars.
  15. Garmin Local @anup-shesh/garmin-local-mcpLocal-first Garmin data warehouse: sync once to SQLite, analyze trends and correlations offline.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.8 GitHub stars.
  16. Gold @thaitrevor/gold-mcpMCP server for XAUUSD gold market data + 4-tier trading toolkit (TA, backtest, SMC, risk).7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.8 GitHub stars.
  17. Disco @leap-labs/discovery-engineFind novel, statistically validated patterns in tabular data — hypothesis-free.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.7 GitHub stars.
  18. Analytics @mcpanalytics/analyticsThe statistical analyst in your AI chat — validated, citable, re-runnable analysis of your data.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.7 GitHub stars.
  19. Aurora @fantasylab-ai/auroraGlass-box statistical analysis for agents: 19 methods, cited findings, measured error rates.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.5 GitHub stars.
  20. Okama @mbk-dev/okama-mcpPortfolio analytics via the okama library: backtests, Monte Carlo, efficient frontier, PNG charts4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.5 GitHub stars.
  21. Math MCP Learning @clouatre-labs/math-mcp-learning-serverEducational MCP server with 17 math/stats tools, visualizations, and persistent workspace2% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.5 GitHub stars.

Also touches on Statistics

207 where it is one part of a bigger job