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.
-
kaggle-mcpgithub.com/arrismo/kaggle-mcpupdated this year
MCP server for Kaggle
MIT ★ 39 -
mcp server for kaggle apis
-
MCP server for interacting with Kaggle competitions
MIT ★ 10 -
—
-
mseep-kaggle-mcpstale
MCP Server for interacting with Kaggle API
pypi mit -
@iflow-mcp/dishant27-kaggle-mcpupdated this year
MCP server for interacting with Kaggle competitions
npm MIT -
mcp-kaggle-toolgithub.com/MikeyBeez/mcp-kaggle-toolupdated this year
MCP server for Kaggle API integration - create, run, and manage Kaggle notebooks programmatically
★ 1 -
kaggle-mcpgithub.com/Galaxy-Dawn/kaggle-mcpupdated this year
A full-featured MCP server for the Kaggle API — competitions, datasets, kernels, models, benchmarks, and discussions.
pypi MIT ★ 4 -
mcp-server-kaggle-execupdated this year
MCP server for executing Python code on Kaggle GPU runtimes (T4/P100/TPU)
pypi MIT -
Kaggle tools for DeepSeek Harness: search and download datasets, competitions, notebooks and models through the Kaggle CLI, plus an optional Kaggle MCP adapter.
npm Apache-2.0 -
Cloudflare Workers MCP server proxying claude.ai tool calls to Kaggle API (kernels, datasets, competitions)
-
Kaggle-MCP: Connect Claude AI to the Kaggle API through the Model Context Protocol (MCP), enabling competition, dataset, and kernel operations through the AI interface.
MIT ★ 36 -
Kaggle-mcpgithub.com/Seif-Sameh/Kaggle-mcpupdated this year
MCP server for the Kaggle API — manage competitions, datasets, kernels, and models from Claude Desktop and any MCP-compatible client.
pypi MIT -
Full Kaggle API as an MCP server (25 tools) for Claude Desktop, Claude Code, Codex, Cursor, Hermes, Windsurf, OpenCode, and more.
MIT ★ 2 -
MCP server built with FastMCP and the Kaggle API that lets Claude search, inspect and download Kaggle datasets using plain-English prompts. Includes three tools, MCP Inspector testing and Claude Desktop setup.
MIT -
This project provides an MCP (Model Context Protocol) server for interacting with Kaggle competitions from Claude Desktop (or any MCP-compatible client)
MIT ★ 4 -
kaggle-mcpgithub.com/parkseokjune/kaggle-mcpupdated this year
Safety-first MCP server connecting Claude to Kaggle (competitions, datasets, kernels, models) — confirm-token gates, submission budget, prompt-injection hardening.
pypi MIT -
Give any coding agent free Tesla T4 x2 GPUs via Kaggle's REST API -- MCP server, CLI, and skill.
pypi MIT -
Kaggle-Dataset-Evaluator-Agentgithub.com/VRYeshwanth/Kaggle-Dataset-Evaluator-Agentupdated this year
AI agent for dataset quality evaluation, ML task inference, and project recommendation using Google ADK and MCP.
-
🏥 HealthGuard AI: Multi-agent clinical monitoring system reducing hospital false alarms by 85% using Gemini 2.0 Flash. Built for Google AI Agents Intensive Bootcamp 2025. Features 5 specialized agents, custom MCP medical tools, real-time sepsis/cardiac detection, and Docker deployment.
★ 3 -
LearnForge-AIgithub.com/Butkii025/LearnForge-AIupdated this year
Multi-agent AI study system for CSE/IT/AI-ML/DS students , Google ADK + MCP + FastAPI + React. Kaggle 2026 Hackathon Project Idea
NOASSERTION -
claude-skill-arc-agi-3updated this year
Install the ARC-AGI-3 Kaggle skill + MCP server for Claude Code
npm MIT -
hireflowgithub.com/Ahmzyjazzy/hireflowupdated this year
HireFlow is an intelligent multi-agent system designed to streamline and automate the new-hire onboarding process. Built as a capstone project for the Kaggle Agents Intensive, it leverages Google's Agent Development Kit (ADK) and the Model Context Protocol (MCP) to create a seamless, efficient, and interactive onboarding experience.
★ 1 -
kgmongithub.com/azxav/kgmonactive
MCP server and CLIs for a local Kaggle competition workspace, with validation, packaging, and guarded submission.
MIT -
kctxgithub.com/vks-g/kctxactive
Turn any Kaggle competition into Claude-ready context — workspace folder, Claude skill, or local MCP server. One curl, one TUI.
MIT ★ 2 -
RoshniAIgithub.com/laibaazeem3250-ship-it/RoshniAIupdated this year
Multi-Agent AI University Guide built using Python, Flask, MCP, and Groq for the Google × Kaggle AI Agents Course.
★ 1 -
Persistent GPU jobs for AI agents. MCP + CLI, hardware-aware scheduling, Kaggle adapter, and recoverable artifacts for Codex and Claude Code.
MIT ★ 21 -
What's in a dataset before you download it: columns, licence and size from Hugging Face, Kaggle and data.gov. A CLI and an MCP server.
MIT -
pipeline-copilotgithub.com/Shreyaskale7/pipeline-copilotupdated this year
Multi-agent sales assistant (Google ADK + custom MCP server) that flags at-risk deals by dollar value and drafts grounded follow-up emails. Built for the Kaggle AI Agents Vibe Coding Capstone.
-
forgeai-ai-agentsgithub.com/Muthukula-kavya/forgeai-ai-agentsupdated this year
ForgeAI — Autonomous AI Startup Platform | 8 specialized AI agents that transform a startup idea into production-ready code, architecture, security policies & docs | Built with Google ADK + Gemini 2.5 Flash + MCP | Google × Kaggle 5-Day AI Agents Capstone
MIT -
Autonomous DFIR triage agent built with Google ADK & FastMCP. 4-phase NLP pipeline: frequency stacking → Isolation Forest anomaly detection → SIGMA rule enrichment → multi-agent LLM analysis. Zero-hallucination via hash-chained provenance. Kaggle AI Agents Capstone — Agents for Business.
Apache-2.0 -
Where my hug at? Tell your AI agent what you want a model to do. It finds what Hugging Face, Kaggle, Zenodo, ModelScope and Roboflow already have for it, models and data alike, what to fine-tune, and what's just code, with every pick checked live.
npm MIT -
Spoiler-aware, multi-agent House of the Dragon S3 companion. Built with Google ADK + a custom MCP server: transcribes official HBO promo captions, cross-references Fire & Blood for book-vs-show diffs, and enforces a per-episode spoiler guardrail. Fully offline-reproducible. Kaggle x Google AI Agents Capstone.
MIT -
MediMategithub.com/leanaraque/MediMateupdated this year
Secure multi-agent medication concierge — Google ADK, custom MCP server (openFDA + RxNorm), deterministic safety guardrails. Google × Kaggle capstone,
-
Chatbot who uses MCP server from hf-articles-search repo with "fastapi-mcp" for RAG and embeddings search to answer question related to science articles from kaggle "News Category Dataset" from HuffingtonPost.
GPL-3.0 -
arthagithub.com/sidhvik17/arthaupdated this year
Multi-agent equity research crew (Google ADK) that writes balanced briefs and refuses financial advice by construction - deterministic prompt-injection guardrail, MCP tool server, 12 tests. Kaggle x Google Agents Capstone.
MIT ★ 2 -
dispatch-agentgithub.com/shivamkrsharma006-lang/dispatch-agentupdated this year
Multi-agent research digest built with Google ADK — MCP tool integration, sanitization against prompt-injection, semantic dedup via embeddings, and a two-layer evaluation gate. Built for the Kaggle × Google AI Agents Intensive capstone.
MIT -
cs651-final-project-kacie-phillippogithub.com/kacie-phillippo/cs651-final-project-kacie-phillippoupdated this year
Final project submission for CS651, Data-Intensive Distributed Computing, at the University of Waterloo. Project includes a data analysis of the "Steam Dataset 2025: Multi-Modal Gaming Analytics" data set from Kaggle, as well as the implementation of an MCP server to talk to the dataset.
-
MCP Server para análisis de datos sobre dataset del Titanic
-
specopt-mcpgithub.com/nafwa03/specopt-mcpupdated this year
DSPy-Powered Prompt & Code Optimization via the Model Context Protocol (MCP).
MIT ★ 1 -
study-planner-agentgithub.com/Sohail-Rasul/study-planner-agentupdated this year
AI-powered study planning assistant built with Google ADK, MCP, FastAPI, and Streamlit.
MIT -
A multi-agent system that parses resumes, evaluates job fit, and drafts tailored cover letters — built with Google ADK + FastMCP.
-
Media discovery platform built by harvesting open datasets, applying machine learning text classification, and implementing Model Context Protocol (MCP) agentic RAG guardrails.
-
Privacy-first multi-agent kitchen concierge : Google ADK + custom MCP server + local SQLite vault
-
MLOps control tower for free-tier training: durable job queue, weekly GPU-hour budget, fail-closed redaction audit, transformer classifiers, a QLoRA recipe and an MCP server for agents.
NOASSERTION -
saferx-companiongithub.com/aldian/saferx-companionupdated this year
Medication safety concierge agent — ADK 2.0 workflow graph, custom openFDA MCP server, PII redaction, and HITL caregiver approval gate
MIT -
@vespermcp/mcp-servergithub.com/vesper/mcp-serverupdated this year
AI-powered dataset discovery, quality analysis, and preparation MCP server with multimodal support (text, image, audio, video)
npm MIT -
Smart-Farming-Advisorgithub.com/Pranith-g/Smart-Farming-Advisorupdated this year
AI-powered Smart Farming Advisor built with Gemini AI, Multi-Agent Systems, MCP Servers, Streamlit, TensorFlow, and SQLite for intelligent agricultural recommendations.
MIT ★ 3 -
Honest first-hour checks for tabular ML, as MCP tools for AI coding agents: inspect, shift check, time/group-aware CV vs no-skill baseline, submission checks
MIT -
krishimitra-multi-agentgithub.com/HARIHARANS24/krishimitra-multi-agentupdated this year
🌾 Multi-Agent AI Farmer Advisory System built with Google ADK, MCP Servers, Streamlit, and Gemini for intelligent crop, weather, pest, fertilizer, market, and government scheme recommendations.
MIT -
rescuemind-multi-agentgithub.com/BALADURGAG24/rescuemind-multi-agentupdated this year
Production-ready multi-agent AI disaster response platform powered by Google Gemini, MCP servers, and Streamlit for emergency coordination, shelter discovery, medical assistance, and government relief.
MIT ★ 2 -
WholeShare: small businesses pool orders to reach supplier price tiers. An AI assistant does the legwork, and PayPal holds the money until the goods arrive right. Powered byPayPal sandbox, webMCP, AG Grid, Bryntum, Kernel, Fireworks AI.
MIT ★ 1