"MCP server for finding research data and models for AI/ML training" matching MCP servers:

A safety-gated Python MCP server for Metabase that lets MCP clients and agents inspect Metabase, run governed queries, and create or maintain dashboards, cards/questions, collections, snippets, permissions, and other Metabase assets through the Metabase REST API.

Enables LLMs to interact with Kibana through composable toolboxes for building dashboards, managing data, and handling alerts, among other operations.

Provides aerodynamic analysis tools through MCP, enabling geometry generation, meshing, CFD solving, and visualization for 2D airfoils.

Enables natural-language evaluation, explanation, and reporting of any trained ML model, including performance metrics, prediction insights, drift detection, and PDF report generation.

A production-grade MCP server that provides tools to fetch historical stock data, company information, and technical indicators (SMA, EMA, RSI, MACD, Bollinger Bands) via yfinance, and includes a Flask web dashboard for visual analysis.

Exposes a time series forecasting model as an MCP tool with built-in audit logging for every call, enabling trustworthy autonomous forecasting.

Enables Claude to read a project's FastStats metrics and then design, validate against real data, and publish charts, dashboards, event markers, and custom data sources. Every write is previewed and dry-run first, with read-only mode and confirmation guards for destructive actions.

Enables open-access academic paper search and lookup via arXiv and OpenAlex, plus journal-quality color palettes for scientific figure styling.

Provides 102 tools for end-to-end data science pipelines, enabling data loading, cleaning, visualization, modeling, and reporting via natural language.

Enables searching and analyzing over 3,400 datasets from the Serbian government open data portal, with built-in charting and data transformation tools.

Enables data engineers and BI professionals to perform data pipeline development, quality assurance, visualization, and API integration locally with AI assistance.

A data visualization MCP server built on FastMCP, providing 32 tools for chart generation, report building, and data processing.

Enables host assistants to discover and read the toolkit’s research methods over a local stdio MCP connection, supporting research planning, literature work, scientific reasoning, writing, figures, and academic document workflows. It does not itself search scholarly databases, generate research results, compile documents, or call models.

Provides football analytics tools including player scouting, comparisons, market-value filters, expected-goals tables, match-by-match form, team attacking profiles, match search, shot maps, and more for 10 leagues.

Enables AI-native statistical analysis and reproducible research workflows through MCP, including natural language planning, protocol-based analysis, Python/R cross-validation, and publication-ready figure generation.

Enables scientific data introspection and visualization of VTK datasets with format-adaptive metadata extraction and interactive 3D visualization through MCP tools.

Enables data analysis and visualization operations such as loading CSV/Excel/JSON files, computing summary statistics, generating charts, and exploring datasets via SSE/HTTP.

Enables your own ChatGPT to build and manage a collaborative work board—dashboards, categories, datasets, monitors, and policies—through typed WebMCP tools, with human approval, audit trails, and guardrails enforced on every action.

A real MCP server exposing data-analyst tools (SQL querying, schema introspection, stats, charting) over a sales database, with a Gemini agent that discovers and calls those tools at runtime via the standard MCP protocol.

Enables MCP clients like Claude Desktop, Claude Code and Cursor to safely explore local CSV, Excel, Parquet and SQLite files by running guarded read-only DuckDB SQL over a sandboxed data directory. It also supports data profiling, chart generation as image content, and exporting query results, without ever allowing writes or access outside the configured folder.

A natural-language data analyst MCP server that lets users query SQLite sales datasets via MCP tools (list_tables, aggregate, time_series, run_sql) with read-only SQL safety guards, returning results through a FastAPI dashboard.

MCP server for Microsoft Power BI and Fabric, enabling Claude to discover workspaces, semantic models, generate and execute DAX queries, and retrieve report metadata via device-code authentication.

MCP server providing data analytics tools for AI agents to load, clean, analyze data, generate charts and dashboards.

An unofficial MCP server for generating infographics and visuals from text using the Napkin AI API, enabling AI assistants to create professional diagrams, mindmaps, and charts.

Turns a local CSV or XLSX table into a full analysis report — summary statistics, duplicate and missing-value diagnostics, top category frequencies, significant pairwise correlations, a Markdown insights writeup, and an Excel workbook with native interactive charts — entirely offline with no uploads, API keys, or pandas dependency. It runs over stdio or streamable-http behind a free anonymous tier that returns an in-band quota signal rather than silently billing.

Google Search Console for Claude and other MCP clients. Sign in with Google in one click, then ask about clicks, queries, rankings and indexing, export every GSC report as CSV (beyond the 1,000-row UI limit), inspect URLs, submit sitemaps and verify sites. Includes a local SEO dashboard. Free, open source, runs on your computer.

MCP server that renders bar, line, and pie charts from data using QuickChart, returning PNG file paths.

MCP server for AI-driven CAD operations, enabling parametric modeling, build, inspection, measurement, rendering, and diff comparison with STEP, DXF, and GLB export.

Enables AI agents to query Google Trends for search-interest signals, returning stable JSON envelopes with calibrated searches/day estimates, relative comparisons across keywords, related and rising queries, regional interest, and country-level Trending Now data. It also surfaces explicit status and error codes so agents can distinguish partial or failed results from real numbers.

Enables AI assistants to drive a live TradingView chart in Chrome, turning natural-language trading ideas into compiled Pine Script indicators, adding them to charts, and reading back results. It also supports chart navigation, indicator management, screenshots, and strategy tester backtest results.