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. Each candidate is checked by a language model from its name, description and topics, and only actual MCP servers are listed (not clients, SDKs, lists or skills). Package descriptions, licences and links are read from each package's own registry (npm, PyPI, crates.io, NuGet, RubyGems; Go and Maven packages are only checked to exist), and packages the registry no longer has are removed. 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.
-
IBCS-compliant Plotly charts with an AI-ready planning layer and MCP server
MIT -
plotly_mcpgithub.com/a-humphrey/plotly_mcpupdated this year
MCP Server designed to help with the generation of Plotly Charts. Co-Authored by Claude
★ 1 -
Complete Plotly MCP server for Cursor with 49+ trace types and natural language interface
★ 9 -
dust-analyzergithub.com/synapticore-io/dust-analyzerupdated this year
European air quality MCP server — Saharan dust, SO₂, PM2.5 from CAMS/Copernicus as interactive Plotly charts in Claude Desktop. Daily updated, no API key needed.
★ 2 -
AutoPhaseAnalysisgithub.com/jojusmathew/AutoPhaseAnalysisupdated this year
Automated XRD phase identification and Rietveld refinement — a dara tree search explores phase combinations and BGMN-refines each one, no manual peak matching. Ranked solutions with interactive Plotly charts, phase-weight tables, exportable refinement files, and an MCP server for headless AI-agent control.
NOASSERTION ★ 1 -
matlab-mcp-server-pythongithub.com/HanSur94/matlab-mcp-server-pythonupdated this year
MCP server that connects any AI agent to MATLAB — execute code, async jobs, interactive Plotly plots, custom tools, and monitoring dashboard
MIT ★ 4 -
An MCP server that gives AI agents the power to connect to any database, explore schemas, run secure SQL queries, profile data, generate interactive Plotly charts, and upload datasets — all through the Model Context Protocol. Built with FastMCP, SQLAlchemy, and Pandas. Supports SQLite, PostgreSQL, MySQL, and more.
★ 2 -
Vizrogithub.com/mckinsey/vizrono update data
provides tools and templates to create a functioning Vizro chart or dashboard step by step
oci -
MCP server for rendering Mermaid diagrams and converting to images
npm MIT -
An MCP server exposing data science tools (plotting, stats, data exploration) to any LLM client.
pypi MIT -
The Ultimate Chart Generation MCP Server - Built for Performance, Powered by AI
pypi MIT -
Local MCP server for source-grounded Swiss open-data discovery, DuckDB analytics, dashboards, maps, citations, and agent workflows.
MIT -
chronos-agentgithub.com/pradhankukiran/chronos-agentupdated this year
A multi-sector time-series forecasting portal and FastMCP tool server using ensembled Prophet and XGBoost hybrid modeling.
-
nveil-toolkitgithub.com/nveil-ai/nveil-toolkitupdated this year
Python SDK, CLI & MCP server for NVEIL — drive data exploration and visualization from code or an AI agent.
AGPL-3.0 ★ 3 -
MCP server for China National ETS (CEA/CCER) carbon market data — dashboard, query & export tools with 1,100+ trading days (2021-2026)
MIT ★ 4 -
MCP server for Korea ETS (K-ETS) carbon market data — KAU/KCU/KOC dashboard, query & export tools with 21K+ records (2015-2026)
MIT ★ 1 -
DataViz MCP enables humans and AI assistants to display and inspect python outputs including data viz and data apps in real time.
pypi BSD-3-Clause ★ 3 -
SQLMind-Agentgithub.com/ishaans04/SQLMind-Agentupdated this year
AI-powered database intelligence platform with Natural Language-to-SQL, Smart Analytics, Dashboard Generation, MCP integration, and NVIDIA NIM support.
MIT -
daraz-scrapergithub.com/MuhammadHashimRN/daraz-scraperupdated this year
Production Flask service that scrapes Daraz.pk product listings and serves PCA + UMAP analytics via REST + WebSocket API — systemd / ngrok / MCP-automated daily pipeline
MIT -
cnra_gw_dashboardgithub.com/hhaeri/cnra_gw_dashboardupdated this year
A lightweight MCP data pipeline and interactive Dash dashboard for fetching, rendering, and analyzing California Natural Resources Agency CNRA groundwater telemetry.
-
銘柄コードから株価・財務・ニュースを集め、8セクションのHTML株式リサーチレポートを自動生成するエージェント(MCP × Claude Code / LLMなしのCLI版あり) | MCP-based equity research agent — three FastMCP servers, Claude Code skills, and a standalone CLI that produce 8-section interactive HTML research reports.
-
Crawler/SEO companion for Dash apps: /llms.txt, /robots.txt, /sitemap.xml, bot detection, static-HTML prerender, and an MCP bridge. Works with Flask, FastAPI, and Quart backends (Dash 4.1+).
pypi MIT -
Data-Analyze-MCPgithub.com/chaeminyoon/Data-Analyze-MCPupdated this year
MCP data analysis server with 60 expert tools - auto chart recommendation, accessibility-validated chart themes (CVD-simulated, CI-enforced), statistics, ML diagnostics, and inline result display for any LLM (Claude / OpenAI)
MIT ★ 8