Skip to content
➜NextOS

MCP servers for
Data Science Tools

41 servers in the catalog, aggregated from the official MCP registry, the reference server repo, and the community. Showing 41.

Browse the full catalogAdd one to an agent

01The servers

  • 98lukehall/renoun-mcp

    98lukehall/renoun-mcp

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

    Homepage ↗

  • abhiphile/fermat-mcp

    abhiphile/fermat-mcp

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

    Homepage ↗

  • Archerkattri/mathlas

    archerkattri/mathlas

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

    Homepage ↗

  • arrismo/kaggle-mcp

    arrismo/kaggle-mcp

    Connects to Kaggle, ability to download and analyze datasets.

    Homepage ↗

  • aurelio-nakamura/dataloupe

    aurelio-nakamura/dataloupe

    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`.

    npx -y githubHomepage ↗

  • avisangle/calculator-server

    avisangle/calculator-server

    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.

    Homepage ↗

  • BlackMount-ai/blackmount-nlp-mcp

    blackmount-ai/blackmount-nlp-mcp

    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`.

    pip install blackmount-nlp-mcpHomepage ↗

  • bradleylab/stella-mcp

    bradleylab/stella-mcp

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

    Homepage ↗

  • Bright-L01/networkx-mcp-server

    bright-l01/networkx-mcp-server

    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.

    Homepage ↗

  • chohyerinn/filter-mcp-server

    chohyerinn/filter-mcp-server

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

    Homepage ↗

  • ChronulusAI/chronulus-mcp

    chronulusai/chronulus-mcp

    Predict anything with Chronulus AI forecasting and prediction agents.

    Homepage ↗

  • clouatre-labs/math-mcp-learning-server

    clouatre-labs/math-mcp-learning-server

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

    Homepage ↗

  • Daichi-Kudo/llm-advisor-mcp

    daichi-kudo/llm-advisor-mcp

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

    Homepage ↗

  • DataEval/dingo

    dataeval/dingo

    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.

    Homepage ↗

  • datalayer/jupyter-mcp-server

    datalayer/jupyter-mcp-server

    Model Context Protocol (MCP) Server for Jupyter.

    Homepage ↗

  • FantasyLab-ai/aurora

    fantasylab-ai/aurora

    Glass-box statistical analysis: 19 research-grade methods, cited findings, integrity-hashed bundles, and measured detector false-fire rates shipped as a calibration corpus. Agents cite real math instead of inventing it. `uvx aurora-mcp`.

    Homepage ↗

  • gpartin/WaveGuardClient

    gpartin/waveguardclient

    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.

    Homepage ↗

  • growthbook/growthbook-mcp

    growthbook/growthbook-mcp
    Homepage ↗

  • haiiibin/data-profiler-mcp

    haiiibin/data-profiler-mcp

    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`.

    pip install data-profiler-mcpHomepage ↗

  • HumanSignal/label-studio-mcp-server

    humansignal/label-studio-mcp-server

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

    Homepage ↗

  • inity13/decisionmatrix-mcp

    inity13/decisionmatrix-mcp

    Deterministic multi-criteria decision analysis (MCDA): score, rank & explain options against weighted criteria with weighted-sum, weighted-product, or TOPSIS, plus sensitivity analysis (which weights would flip the winner). Exact decimals, stateless. Free hosted endpoint or self-host (MIT). `https://decisionmatrix-mcp.pages.dev/mcp`

    Homepage ↗

  • jjsantos01/jupyter-notebook-mcp

    jjsantos01/jupyter-notebook-mcp

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

    Homepage ↗

  • jonahthan433/cortexcloud-mcp

    jonahthan433/cortexcloud-mcp

    Pay-per-call QUBO/Ising optimization for AI agents: estimate free, solve per run (classical $0.05, hybrid $0.10, quantum $0.85) via x402 (USDC on Base). No API keys. Remote Streamable HTTP at https://api.cortexcloud.org/mcp.

    Homepage ↗

  • kdqed/zaturn

    kdqed/zaturn

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

    Homepage ↗

  • laszlopere/mcp-gnu-units

    laszlopere/mcp-gnu-units

    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`.

    Homepage ↗

  • leap-laboratories/discovery-engine

    leap-laboratories/discovery-engine

    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.

    Homepage ↗

  • lihtness/gnomon-mcp

    lihtness/gnomon-mcp

    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`.

    Homepage ↗

  • mckinsey/vizro-mcp

    mckinsey/vizro

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

    Homepage ↗

  • mrnh/rigor

    mrnh/rigor

    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`.

    Homepage ↗

  • optuna/optuna-mcp

    optuna/optuna-mcp

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

    Homepage ↗

  • phisanti/MCPR

    phisanti/mcpr

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

    Homepage ↗

  • phuongrealmax/code-guardian

    phuongrealmax/code-guardian

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

    Homepage ↗

  • playidea-lab/pcq

    playidea-lab/pcq

    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.

    Homepage ↗

  • pramod/kaggle

    krishnapramodparupudi/kaggle-mcp-server

    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.

    Homepage ↗

  • reading-plus-ai/mcp-server-data-exploration

    reading-plus-ai/mcp-server-data-exploration

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

    Homepage ↗

  • ShipItAndPray/mcp-compress

    shipitandpray/mcp-compress

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

    Homepage ↗

  • ShipItAndPray/mcp-turboquant

    shipitandpray/mcp-turboquant

    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.

    Homepage ↗

  • subelsky/bundler_mcp

    subelsky/bundler_mcp

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

    Homepage ↗

  • tufantunc/axiom-advanced-math-mcp

    tufantunc/axiom-advanced-math-mcp

    Exact symbolic mathematics from a real computer algebra system (Giac/Xcas compiled to WebAssembly, no network calls): calculus, equation solving, linear algebra, combinatorics, and independent verification of a claim. Also runs as a shell command, so agents can use it as a skill with no MCP configuration. `npx -y axiom-math`

    npx -y axiom-mathHomepage ↗

  • Whatsonyourmind/oraclaw

    whatsonyourmind/oraclaw

    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`.

    npx -y @oraclaw/mcp-serverHomepage ↗

  • zcaceres/markdownify-mcp

    zcaceres/markdownify-mcp

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

    Homepage ↗

02Other categories

6,000+ servers · one catalog · any agent

Give an agent new tools.
Add any MCP server in minutes.

Browse the catalogThe whole OS