MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
data-science-ai-mcpgithub.com/csoai-org/data-science-ai-mcpupdated this year
Data Science Ai tools for AI agents. Capabilities: feature importance, model comparison, dataset profiler. Built by MEOK AI Labs.
pypi MIT License -
mcp-data-sciencegithub.com/AstyanM/mcp-data-scienceupdated this year
MCP server that gives an LLM 48 tools to perform complete CSV data cleaning and preprocessing pipelines
★ 3 -
data-forge-mcpgithub.com/angrysky56/data-forge-mcpupdated this year
Data-Forge is a Model Context Protocol (MCP) server that transforms any LLM into a powerful Data Science Assistant. It provides a suite of high-performance tools for data loading, cleaning, validation, profiling, feature engineering, and visualization.
MIT ★ 2 -
@frontlinesystems/rason-mcp-serverhttps://www.solver.com/rasonupdated this year
Build, solve, and analyze RASON optimization, simulation, data science, and decision models
npm SEE LICENSE IN LICENSE -
Noesisgithub.com/chetan0220/Noesisupdated this year
Noesis is an AI‑Powered Data Analysis Platform which streamlines data science workflows by combining Large Language Models with the Model Context Protocol (MCP). It offers automated exploratory analysis, data transformation, data cleaning and data vizualization
★ 1 -
mcp-servers-collectiongithub.com/mlnjsh/mcp-servers-collectionupdated this year
Collection of MCP (Model Context Protocol) servers for Claude — Manim, ML/Data Science tools, Zomato, Swiggy, and more
★ 1 -
A ledger of experimental data and process, kept encrypted and backed by proof. GitHub for code, Hugging Face for models, Provena for verifiable science.
NOASSERTION -
MCP server giving LLM agents access to databases, files, graphs, and a full data science toolkit — 52 tools across 13 database types and 20+ file formats
Apache-2.0 ★ 15 -
A unified life science data layer for your AI agents - genomics, proteomics, drug discovery, clinical trials across 300+ databases.
MIT -
insight-blueprintgithub.com/etoyama/insight-blueprintupdated this year
MCP server for data science analysis design management
pypi MIT -
MCP servers for Protein Data Bank, ChemBL, and other life science data (WIP), with Ollama client for local testing.
★ 12 -
CASDA-MCPgithub.com/jbwod/CASDA-MCPupdated this year
Model Context Protocol server for the CSIRO ASKAP Science Data Archive (CASDA). It converts an AI client structured selections into explicit, auditable archive operations.
BSD-3-Clause -
Data Science, MCP Server for LLM Agents
MIT ★ 2 -
simple-obspygithub.com/Fahim-Azwad/simple-obspyupdated this year
Simple MCP server enabling Claude Desktop to download earthquake and waveform data via ObsPy - (Developed at the request of Professor Weiqiang Zhu, Earth & Planetary Science, UC Berkeley)
-
codenavgithub.com/ajacobm/codenavupdated this year
Data Science platform for code structure analysis, trace event-action chains through graph queries; perform code diagnostics and more! Notebooks, Force-directed graph visuals; follow your agent as it updates your files.
MIT ★ 1 -
RASONno update data
A complete AI infrastructure for analytical modeling — not just a REST API wrapper. Provides any MCP-compatible AI assistant with access to **[RASON](https://www.solver.com/rason)** by [Frontline Systems](https://www.solver.com) for building, analyzing, and solving optimization, simulation, data science, and decision models. Includes a searchable library of nearly 200 example models, starter templates for every model type, structural model analysis, and guided workflows for solving and result interpretation. An AI assistant connected to this server can formulate a model from a business problem description, find relevant examples, explain model structure, submit it for solving, and present results in a goal-oriented way — closing the loop with suggested next steps and improvements. **Example interactions:** - "Find me a portfolio optimization example" - "Build a scheduling model for 8 employees with shift constraints, solve it, and show the schedule" - "This model is infeasible — run diagnostics and suggest which constraints to relax"
smithery -
A Python toolkit — AI for Science
AGPL-3.0 ★ 85 -
Distributed Data Processing Pipeline for MCP.
AGPL-3.0 ★ 33 -
An MCP server for Apache Doris & VeloDB
Apache-2.0 ★ 15 -
aleatoric-engine-mcpgithub.com/aleatoric-systems/aleatoric-engine-mcpupdated this year
Aleatoric Engine Causal AI Data Generator MCP Client
Apache-2.0 ★ 1 -
spreadsheet-dlgithub.com/lair-click-bats/spreadsheet-dlupdated this year
Universal spreadsheet definition language. Define once in Python or YAML, export to ODS/XLSX/PDF. Domain plugins for science, engineering, finance. Native MCP server for AI integration.
pypi MIT -
Data Agents are intelligent assistants built by data engineers to help non-data professionals navigate the organization’s data infrastructu
MIT ★ 25 -
Solvro internal MCP server
★ 6 -
gretl-pymcpgithub.com/gretl-project/gretl-pymcpupdated this year
A MCP server for gretl (open-source econometrics & statistics program)
MIT -
Strata is a notebook your coding agent can drive, and everything it computes stays.
pypi Apache-2.0 ★ 5 -
High-performance, memory-safe, and open-source statistical analysis package in 100% pure Safe Rust
Apache-2.0 ★ 53 -
Unified research-data acquisition MCP — search & fetch datasets across Zenodo, DataCite, NCBI omics (GEO/SRA/BioProject), and literature (PubMed/OpenAIRE) behind one normalized model.
pypi MIT ★ 4 -
mcp_wbgapi360github.com/MaykolMedrano/mcp_wbgapi360updated this year
Enterprise-grade Async Python Client for World Bank Data360 API with hybrid MCP support for AI Agents (Claude/OpenAI).
MIT ★ 2 -
A powerful MCP server for AI-driven Jupyter Notebook management and execution
pypi MIT -
Mobusgithub.com/mobus-ai/Mobusupdated this year
Search, preview, and analyze datasets from 20+ platforms via a single MCP connector. Works with Claude instantly.
MIT ★ 29 -
Search the Metropolitan Museum of Art collection and retrieve artwork records and open-access images using an MCP server via STDIO or HTTP.
Apache-2.0 -
🌍 MCP server giving Claude live environmental data: air quality, wildfires, and weather, plus statistical anomaly detection and causal inference (DoWhy) to explain why pollution spikes happen.
MIT -
mcptoolsgithub.com/tnCas/mcptoolsupdated this year
Model Context Protocol (MCP) server for R. Provides tools for median-based data imputation, outlier detection via the 1.5x IQR rule, and Pearson correlation analysis
-
arxiv-research-mcpgithub.com/smorande/arxiv-research-mcpupdated this year
MCP server for data scientists — search ArXiv papers, find code, get citations, track SOTA benchmarks. Zero API keys needed.
MIT ★ 1 -
Local data workbench a local language model drives over MCP: ingest, versioned cleaning, quality rules, charts, dashboards as code and quick models. Part of the Hoard family.
MIT -
Linter for LLM fine-tuning datasets: catches broken chats and tool calls, context overflow, leaked keys, PII and eval contamination before you train. CLI, Python API, MCP server, GitHub Action.
pypi NOASSERTION ★ 5 -
MCP server providing tools to access EFSA's comprehensive OpenFoodTox Chemical Hazards in food dataset
MIT ★ 5 -
A comprehensive MCP (Model Context Protocol) server providing 40+ statistical analysis tools forAI assistants. Supports descriptive statistics, hypothesis testing, regression analysis, and advanced statistical computations using NumPy and SciPy.
★ 3 -
projeto-rag-geometricogithub.com/Dellos12/projeto-rag-geometricoupdated this year
"Motor de RAG fundamentado em Geometria da Informação e Variedades Estatísticas. Implementação industrial com Docker, FastAPI e MCP para alinhamento vetorial de alta precisão."
-
A coach's morning report from your Garmin data, for any LLM via MCP.
Apache-2.0 -
A statistical analyst in your AI chat. Bring a dataset and a question, get back a citable, re-runnable analysis with its method named. Works in Claude, Cursor, and any MCP client.
MIT ★ 9 -
Ask your AI assistant real questions about your data and get answers you can rely on — an MCP server with 45 analysis tools that pick the right statistical method themselves and tell you how much to trust the result.
MIT ★ 10 -
Lock a notebook's outputs with a test, catch its hidden state, then let your agent refactor it into a pipeline that provably gives the same results.
MIT -
MCP server (stdio) for AI agents to safely read, edit and run local Jupyter notebooks — zero service, CAS-guarded edits, resumable execution.
npm MIT -
Validated analytics agent for CSV/Excel. LLMs plan - as a JSON plan or a bounded tool-calling loop - while deterministic pandas/scipy/DuckDB computes and re-verifies every number. No arbitrary code execution: the model only selects audited operations.
MIT ★ 4 -
Read, edit and run local Jupyter notebooks from any AI agent — for students, data work and teaching. Zero service (one npx line), CAS-guarded edits that can't silently corrupt your file, resumable execution.
npm MIT ★ 3 -
breezemlgithub.com/venomez-viper/breezemlupdated this year
A beginner-friendly, production-aware ML workflow layer for students, analysts, and AI agents. Train, compare, explain, export, and deploy scikit-learn models without the boilerplate.
MIT ★ 3 -
Re-run the work, recompute the number, block the wrong one before it ships — a deterministic guardrail for AI-computed results. CLI · Claude Code hook · MCP.
MIT -
🎓 ICIL — Intelligence Campus Interactive Library. 243 courses · 32 faculties · 10 MCP tools. Curated context injection for AI agents. P@3=86.5%, R@3=98.9%.
MIT -
ML Referee evaluates whether candidate features add predictive value beyond a baseline for machine learning and forecasting. AI agents can preflight data, request quotes, and run authorized evaluations through MCP. Invite-only beta. Website: MCP endpoint: https://api.mlreferee.com/mcp
MIT -
Shared Single-file memory layer for all your agents, sub mili-second RAG over text, photo and video on Apple Silicon.. No Server. No API. One File. Pure Swift
npm Apache-2.0 ★ 810 -
MCP server that lets Claude explain ML model predictions with SHAP: feature importance, per-prediction explanations, what-if analysis and plots. Read-only and works with any joblib model.
-
End-to-end ML toolkit automating the complete workflow — data profiling, preprocessing, feature engineering, model selection, training, validation, explainability, drift monitoring, fairness checks, and interactive HTML reporting. Includes a full CLI for zero-code ML pipelines. Python 3.10+.
MIT ★ 16 -
Agent-native Stata bridge for empirical research — run DiD/IV/RDD and publication-ready tables from Claude Code, Jupyter, or VS Code on one token-economy result schema, with StatsPAI cross-validation. | 面向实证研究的智能体 Stata 桥接器——在 Claude Code、Jupyter、VS Code 中用一套省 token 的结果格式跑 DiD/IV/RDD 与出版级表格,并支持 StatsPAI 跨栈交叉验证。
MIT ★ 55 -
MCP server for editing Jupyter notebooks (.ipynb) with 23 cell-level tools: create, read, search and restructure cells, manage outputs and metadata, and execute cells on a live Jupyter kernel (python3 built in; R, Julia via installed kernels). Built on nbformat and jupyter_client.
MIT -
FYP-XploitEye-Web-and-System-Vulnerabilities-using-Agents-LLMs-github.com/shoaib1522/FYP-XploitEye-Web-and-System-Vulnerabilities-using-Agents-LLMs-updated this year
XploitEye is a state-of-the-art, AI-powered multi-agent cybersecurity platform designed to automate the complete Cyber Kill Chain. By orchestrating advanced Large Language Models (LLMs) and industry-standard security tools, XploitEye provides a unified interface for both Red Team (Offensive) and Blue Team (Defensive) operations.
-
MCP server for editing R Markdown (.rmd) documents with 24 cell-level tools: create, read, search and restructure cells, read and set knitr chunk options and YAML frontmatter keys, and run chunks on a live Jupyter kernel (R via IRkernel; Python, Julia via installed kernels). Built on PyYAML and jupyter_client.
MIT -
AI-agent-native low cycle fatigue strain-life analysis. Python library plus MCP server: reduce strain-controlled test data, fit Basquin, Coffin-Manson, and Ramberg-Osgood models, predict life with mean-stress corrections, and save results for recall.
MIT -
Temporal memory system for AI assistants with human-like forgetting curves. All data stored locally in human-readable formats: JSONL for short-term memory, Markdown (Obsidian-compatible) for long-term. Memories naturally decay unless reinforced. Features knowledge graphs, smart prompting, and MCP server integration for Claude.
AGPL-3.0 ★ 39