Data Science Tools MCP servers

Predict anything with Chronulus AI forecasting and prediction agents.

3 tools · Combine Chronulus with local data, Forecast using uploaded files

🎖️ 📇 🏠 🪟 🐧 🍎 — Tools for creating and interacting with GrowthBook feature flags and experiments.

5 tools · growthbook_api_read, growthbook_api_write

The ultimate math engine unifying SymPy, NumPy & Matplotlib in one powerful server. Perfect for developers & researchers needing symbolic algebra, numerical computing, and data visualization.

Unit conversion and dimensional analysis backed by the bundled GNU units database (3000+ units, compound expressions, reduction to SI base units). Offline and deterministic. `uvx mcp-gnu-units`.

Create, read, validate, and save Stella system dynamics models (.stmx files in XMILE format) for scientific simulation and modeling.

A comprehensive Go-based MCP server for mathematical computations, implementing 13 mathematical tools across basic arithmetic, advanced functions, statistical analysis, unit conversions, and financial calculations.

An MCP server to convert almost any file or web content into Markdown

Real-time LLM/VLM model comparison with benchmarks, pricing, and personalized recommendations from 5 data sources. No API key required.

Airtight math for agents: 3.7M-theorem search, PSLQ constant ID, OEIS, real Lean kernel checks, applicability checklists. No LLM inside, no API key.

Educational MCP server for math operations, statistics, visualization, and persistent workspaces. Built with FastMCP 2.0.

Structural observability for AI conversations. Detects loops, stuck states, breakthroughs, and convergence across 17 channels without analyzing content.

Physics-based anomaly detection via MCP. Uses Klein-Gordon wave equations on GPU to detect anomalies with high precision (avg 0.90). 9 tools: scan, fingerprint, compare, token risk, wallet profiling, volume check, price manipulation detection.

Link multiple data sources (SQL, CSV, Parquet, etc.) and ask AI to analyze the data for insights and visualizations.

Run Jev AI typed decisions (choice, score, noul) on jevx.org and get calibrated probabilities on every option. Zero-shot: criteria live in the request, no training or fine-tune to change the label set. `npx jevx-mcp`.

This Kaggle MCP Server makes Kaggle more accessible by letting you browse competitions, leaderboards, models, datasets, and kernels directly within MCP, streamlining discovery for data scientists and developers.

LLM quantization via tool call. Convert models to GGUF, GPTQ, and AWQ formats. Recommend optimal quant settings, evaluate quality, and push to Hugging Face Hub.

Data compression MCP server. 7 tools for gzip, brotli, deflate, and TurboQuant quantization. Auto-selects best algorithm. 60x compression on docs. Zero dependencies.

Official MCP server enabling seamless orchestration of hyperparameter search and other optimization tasks with [Optuna](https://optuna.org/).

Deterministic batch tools so LLM agents stop next-token-guessing dates and math. Rich `now()` snapshot (18 fields), `calendar(ops)` batch dispatcher (diff/until/since/add/weekday/business_days, natural-language parsing), `calc(expressions)` Python eval with math+stats pre-loaded, and Pint-based unit conversion. One wiring for dates + math + units. Listed in the official MCP Server Registry. `uvx gnomon-mcp`.

Deterministic calculation for AI agents: exact-precision math (avoids float64 overflow), date arithmetic (leap years, business days), unit conversion, statistics, subnet math, haversine distance, base conversion, and Levenshtein distance. 15 tools, 100% local, no network calls, no API keys, no telemetry. `npx -y polymath-megablaster-mcp`.

Enables autonomous data exploration on .csv-based datasets, providing intelligent insights with minimal effort.

Model Context Protocol for R: enables AI agents to participate in interactive live R sessions.

Profiles tabular data files (CSV, TSV, Parquet, Excel, JSON) for LLM agents: one-call dataset overview, per-column statistics, a data-quality audit (missing values, duplicates, mixed types, outliers), and memory-saving dtype suggestions. Pure Python (pandas); files are read locally and nothing leaves your machine. `pip install data-profiler-mcp`.

Decision intelligence MCP server with 19 algorithms (bandits, Monte Carlo, constraint optimization, forecasting, anomaly detection, risk analysis, graph algorithms), 28 MCP tools. Install via `npx -y @oraclaw/mcp-server`.

Classical hypothesis testing, effect sizes, power/sample-size, and multiple-comparisons correction, computed from scratch and returned as a cited, assumption-checked answer instead of a number recalled from training data. `uvx rigor-mcp`.

Numerical methods MCP server for root finding, numerical integration, differential equations (RK4), and Lagrange interpolation.

AI-powered code refactor engine with 80+ MCP tools for code analysis, hotspot detection, complexity metrics, persistent memory, and automated refactoring plans.

Deterministic local text analysis: sentiment, readability scoring, keyword extraction, text similarity, summarization, and language detection across 18 languages. Pure Python, zero heavy dependencies, 42 KB wheel. Install: `pip install blackmount-nlp-mcp`.

Model Context Protocol (MCP) Server for Jupyter.

Superhuman exploratory data analysis that finds the feature interactions and subgroup effects that LLMs and manual exploration miss — with p-values, effect sizes, and literature citations. Data goes in, validated insights come out. Free for public data.

connects Jupyter Notebook to Claude AI, allowing Claude to directly interact with and control Jupyter Notebooks.

Agent-operable ML experiment contract (cq.yaml + JSON contracts) with a built-in MCP server exposing 14 tools (resolve/inspect/run/validate/describe/compare/lineage) for running, validating, and tracing experiments across any framework (PyTorch / HF Trainer / Lightning / sklearn / XGBoost). Apache-2.0.

Compares approximate filter data structures (Bloom, Counting Bloom, Cuckoo, SuRF) via MCP

Create, manage, and automate Label Studio projects, tasks, and predictions for data labeling workflows.

Enables agents to query local information about dependencies in a Ruby project's `Gemfile`.

MCP server for the Dingo: a comprehensive data quality evaluation tool. Server Enables interaction with Dingo's rule-based and LLM-based evaluation capabilities and rules&prompts listing.

The first NetworkX integration for Model Context Protocol, enabling graph analysis and visualization directly in AI conversations. Supports 13 operations including centrality algorithms, community detection, PageRank, and graph visualization.

Local, offline access to tabular data for AI assistants: list/describe/preview/query CSV/TSV/JSON/Parquet/Excel files, diff two datasets, and generate a self-contained interactive HTML explorer to open in any browser — nothing leaves your machine. Install via `npx -y github:aurelio-nakamura/dataloupe mcp`.

Tools and templates to create validated and maintainable data charts and dashboards.

Connects to Kaggle, ability to download and analyze datasets.