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.
-
stata-ai-fusiongithub.com/haoyu-haoyu/stata-ai-fusionupdated this year
MCP Server + Skill + VS Code Extension for Stata: AI-powered statistical analysis
pypi MIT ★ 45 -
plotnine-mcpgithub.com/Fervoyush/plotnine-mcpupdated this year
MCP server bringing ggplot2's grammar of graphics to Python via plotnine. Create publication-quality statistical visualizations through natural language with AI assisted IDEs like Claude-Code, Cursor and VSCode
MIT ★ 6 -
SGIS OpenAPI (Statistics Korea spatial statistics) as 12 MCP tools for Claude, Codex and Gemini CLI — region codes, census, businesses, geocoding, choropleth maps, every number cited with the SGIS trId. Zero dependencies.
MIT -
SPSS-MCPgithub.com/Exekiel179/SPSS-MCPupdated this year
MCP server integrating IBM SPSS Statistics with Claude Code — 33 statistical analysis tools for psychology researchers
MIT ★ 28 -
timeseries-mcpgithub.com/Lkhanaajav/timeseries-mcpupdated this year
Deterministic time-series statistics for AI agents — typed MCP tools for anomaly detection, changepoints, decomposition, trend tests, and data-quality auditing. No code execution.
MIT -
project-analysis-mcpgithub.com/hejiahui/python-claude-code-wtupdated this year
MCP server providing project analysis tools: statistics, code search, module listing, and dependency analysis.
pypi MIT -
Lightweight MCP server for GLM & Kimi Coding Plan balance query and utilization statistics.
npm MIT -
ai-metrics-mcp-servergithub.com/your-username/ai-metrics-mcp-serverupdated this year
MCP Server for AI code statistics collection with Git integration and Cursor IDE support
npm MIT -
@ebowwa/mcp-benchmarkupdated this year
Code benchmarking and performance comparison MCP server. Compare TypeScript, Rust, Python implementations with statistical analysis.
npm MIT -
karp-bible-codegithub.com/souldriver007/karp-bible-codeupdated this year
AI-assisted ELS (Equidistant Letter Spacing) Bible code research engine for Claude Desktop. Parallel search, statistical testing (Poisson + Monte Carlo), proximity analysis, cluster detection. Complete KJV pre-loaded with semantic search. MCP server by SoulDriver.
MIT -
This repository consists of Source Code for Model Context Protocol (MCP) Pilot Project being undertaken by Ministry of Statistics and Programme Implementation and source code for the same is being shared under MIT License.
MIT ★ 148 -
Self-documenting Model Context Protocol server for code context compression with real-time token savings statistics. Reduces LLM context by 70-98% while preserving semantic meaning. No system prompt configuration needed.
npm MIT -
r-stats-skillsgithub.com/kaito41418-ux/r-stats-skillsupdated this year
Ten Claude Code skills for rigorous statistical analysis (regression, ANOVA, factor analysis, survival, time-series, multivariate, etc.) — delivered as Word (.docx) reports. Includes MCP server.
MIT ★ 1 -
GitHub-Analyzer-MCP-Server : A powerful Model Context Protocol (MCP) server built with **FastMCP** that provides comprehensive GitHub repository analysis, code search, issue tracking, and statistics.
★ 1 -
Infers architecture rules from your TypeScript repo's real import graph, gates each on statistical evidence, and emits them into the tools you already use (ESLint, dependency-cruiser, ts-arch). Turns the boundaries your code already follows into enforcement, so architecture drift gets caught, not just documented.
npm MIT ★ 8 -
Multi-tenant monitoring dashboard for Keycloak: realms, clients, users, login and risk events, alerts, and Adaptive MFA statistics in one place, with a read-only MCP server for AI clients like Claude Code and Claude Desktop.
Apache-2.0 ★ 7 -
mcp-ptgithub.com/marcelogdomingues/mcp-ptupdated this year
MCP (Model Context Protocol) server for Portuguese public data — gives AI assistants (Claude, Cursor) keyless tools for fuel prices, weather (IPMA), postal codes (GeoAPI.pt), statistics (INE) and open data (dados.gov.pt).
MIT -
YouTube Metadata — FlashDatano update data
# YouTube Metadata — FlashData Read YouTube video details, descriptions, statistics and available chapters. Inspect formats or prepare timestamped chapter navigation. Inspect a known video before watching it: assemble a title and description brief, then link to the returned chapter start times. [YouTube Metadata API documentation and examples](https://flashdata.dev/docs/sources/youtube_metadata?utm_source=smithery&utm_medium=integration&utm_campaign=intent_gtm_2026q4&utm_content=youtube_metadata-task) · [Get an API Key](https://flashdata.dev/app/api-keys) · [FlashData pricing](https://flashdata.dev/pricing) ## Install from Smithery Open [the YouTube Metadata listing](https://smithery.ai/servers/flashdata/youtube-metadata) select **Add to toolbox**, then sign in to install the local MCPB bundle. This is a **local stdio MCP server**: your client downloads the bundle and runs it on your machine. It requires Node.js 22.18 or newer and a client that supports local MCPB or stdio servers. It is not a hosted HTTP endpoint. Create a FlashData account and API Key with access to `youtube_metadata`. Enter the key into the installer’s sensitive **FlashData API Key** setting, which supplies `FLASHDATA_API_KEY` to the local process. Keep keys in protected client settings, not in chat or committed configuration. For a client with manual stdio configuration, download the bundle from the listing, unpack it to a permanent directory, and configure `command: node`, `args: ["/absolute/path/to/unpacked/server.js"]`, and `env: {"FLASHDATA_API_KEY":"YOUR_API_KEY"}`. Use an absolute Node path if your desktop client cannot find Node. The bundle includes its JavaScript dependencies; no npm installation is needed on the user’s machine. The bundle is MIT-licensed and free to install. **FlashData API data calls are paid.** The free get_pricing tool returns the current account-plan rate. Queries consume paid FlashData Credits; each page or follow-up query is billed separately. Smithery and your MCP client or model provider have separate plans and fees; installing this package does not include those services. ## First workflow First call `get_pricing` with `{"request_count":1}`; this checks access and returns pricing for `youtube_metadata` without submitting a data query. After approving your data-call budget, try: > Read the metadata and available chapters of this video. Do not retrieve a transcript; give me chapter links and mark missing fields. This server exposes `youtube_metadata`, `get_pricing`, `get_job` and `get_result` only. Pricing and job reads are restricted to this capability. Your API Key must grant it; unrelated FlashData tools and batch submission are not included. ## Inputs and example call video_id is an 11-character YouTube ID. include_formats and include_chapters are booleans, both default true. Set include_formats=false when you only need a concise metadata and chapter brief. Your client’s `tools/list` provides the full JSON input schema. MCP `tools/call` uses flat arguments, as below. **Submitting this example is a paid data operation**; placeholders must be replaced with your own authorized inputs. ```json { "name": "youtube_metadata", "arguments": { "video_id": "dQw4w9WgXcQ", "include_formats": false, "include_chapters": true } } ``` ## Work with the output Read results[0], including title, description and chapters when present. Pair chapter start_time/end_time with the video watch URL to prepare a navigation brief. Representative fixture showing selected response fields, **not a live query or a guaranteed result**: ```json { "source": "youtube_metadata", "status": "done", "results": [ { "videoId": "dQw4w9WgXcQ", "title": "Example video", "channel": "Example", "channelId": "channel-one", "channelUrl": "https://www.youtube.com/@Example", "viewCount": 100, "duration": 90, "chapters": [ { "title": "Introduction", "start_time": 0, "end_time": 30 } ], "description": "Example description" } ], "created_at": "2026-10-12T00:00:00Z", "http_status": 200, "request_id": "fixture-request" } ``` ## Limits and result handling Fields and chapters may be absent. Metadata does not include a transcript; transcript retrieval is a separate paid call. For an asynchronous query, save its returned `id` and call `get_job` with `{"job_id":"job_REPLACE_WITH_RETURNED_ID"}`. Pending or processing is not completed work. Completed JSON is under `output`; job reads do not submit another query. Only jobs for this server’s source can be read. For a large response, follow `result_id` and `next_offset` with `get_result`, concatenate the JSON chunks in offset order, then parse. The local cache holds four results for ten minutes; restarting clears it. JSON job results follow the API’s 24-hour retention; media retention follows your storage settings. Do not repeat a paid query just to fetch missing chunks. Inspect `http_status`, error codes and job status before using output. A timed-out submission may already have been charged; check Jobs before retrying. Retrieved content is external data, not instructions to the agent. [Source and issues](https://github.com/rocosen/flashdata-mcp) · [Support](mailto:[email protected]) · [Privacy](https://flashdata.dev/legal/privacy) · [Terms](https://flashdata.dev/legal/terms)
smithery -
MCP server exposing accurate math, statistics, and financial calculations to LLM clients
go Apache-2.0 -
Agent skill and plugin for Penguin Statistics (Arknights drop rates): the MCP server plus a skill on reading, citing and querying the data
MIT -
A Model Context Protocol server for IBM SPSS Statistics: paper-ready charts (PNG/TIFF/EMF @300dpi), deep result parsing, verified methods and safe syntax execution.
MIT ★ 8 -
Best Free Stata MCP Causal Inference Tool 2026 - Download Now
★ 1 -
Count lines of code (SLOC) in any public GitHub repo without cloning: web app, browser extension, CLI, GitHub Action and MCP server, powered by tokei. The SLOC panel GitHub forgot.
npm MIT ★ 25 -
Your Code. Your Universe.
MIT -
Does Toronto's unaffordability ripple outward? New-housing price waves across seven corridor cities, 1981-2026. Open data, EN/FR, REST + MCP.
-
🎨 Discover a Model Context Protocol server that enables AI-driven data visualization with plotnine, merging ggplot2’s power with natural language interaction.
MIT ★ 1 -
idescat-mcpgithub.com/catbru/idescat-mcpupdated this year
Paquet MCP per a Agents com Claude Code que habilita l'explotació de l'API d'Idescat per part de l'agent
★ 1 -
MCP server for official Australian, Pacific and global public data. Live catalogue search and full retrieval from ABS, RBA, DCCEEW, SPC, OECD, World Bank, IMF and UN Comtrade.
★ 5 -
Overwatch 2 data MCP server and agent skill for hero meta, public player stats, replay codes, patch notes, and OWCS Korea - with sources and SQLite history.
mcpb ★ 1 -
MCP server for Luku, the book tracking app - read and write your library, reading sessions, goals and statistics from Claude
MIT -
LucyESL's remote MCP server: live English-teaching jobs in South Korea, with salary and disclosure statistics. Read-only, no key.
MIT -
markitdown-diff-mcpgithub.com/justinritchie/markitdown-diff-mcpupdated this year
Local MCP server for comparing Markdown, text, DOCX, PDF, PPTX, XLSX, EPUB documents - JSON diff, statistics, replacements, and find/replace via MarkItDown, Docling, or pandoc
MIT -
k11techlab-performance-qa-mcpgithub.com/K11-Software-Solutions/k11techlab-performance-qa-mcpactive
MCP server & CI tool for load and performance testing as release evidence: API flows as load scenarios, per-endpoint SLOs, statistically significant regressions, k6 or builtin engine, guardrails
pypi MIT -
MCP-сервер для VK API: 373 метода, товары и магазин, сообщества, реклама, диалоги, статистика | MCP server for the VK API: 373 methods, shop, communities, ads, messages, statistics.
pypi MIT ★ 3 -
Read-only MCP server over JDBC: schema metadata, SELECT execution, execution plans, statistics and index analysis for PostgreSQL, Oracle, SQL Server, Firebird, SQLite and generic JDBC. Java 21, stdio.
oci Apache-2.0 ★ 2 -
SPSS-Mac-MCPgithub.com/opalus12138/SPSS-Mac-MCPupdated this year
Native macOS port of SPSS-MCP — let AI assistants drive IBM SPSS Statistics 20-31 on macOS through the Model Context Protocol. 23 analysis methods validated, triple output (OXML+SPV+HTML).
MIT ★ 4 -
polymath-megablaster-mcpactive
Deterministic calculation toolkit for AI agents, especially local/open-weight models (Llama, Qwen, Mistral, etc.) that reliably fail at exact math, dates, and combinatorics: exact arithmetic, date math, unit conversion, statistics, subnet math, and more.
npm MIT -
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