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.
-
MCP server exposing HarmonyOS best-practices docs + reference code for retrieval during development.
npm MIT -
mcp_project_explorationgithub.com/7pandeys/mcp_project_explorationupdated this year
This project implements a minimal, practical Model Context Protocol (MCP) to store, version, and retrieve contextual fragments for LLMs and model-driven agents.
-
A powerful knowledge management system that forges wisdom from experiences, insights, and best practices. Built with Qdrant vector database for efficient knowledge storage and retrieval.
MIT ★ 4 -
An intelligent code memory system that leverages vector embeddings, structured databases, and knowledge graphs to store, retrieve, and analyze code patterns with semantic search capabilities, quality metrics, and relationship modeling. Designed to enhance programming workflows through contextual recall of best practices, algorithms, and solutions.
MIT ★ 8 -
Save what you learn with Claude Code or Codex and review it with FSRS spaced repetition
-
Study planner for the terminal and MCP: schedules reviews, tracks repeat mistakes and checks mastery from the attempts you record. Leaves graded questions to you.
AGPL-3.0 ★ 1 -
Explain-it-back as an MCP connector: it grounds a check in your own sources, scores it with verified evidence (not model vibes), and resurfaces what you don't yet know. Local-first, opt-in, no telemetry.
MIT