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.
-
language-learning-mcpgithub.com/MahammadNuriyev62/language-learning-mcpupdated this year
Interactive language learning MCP App for Claude.ai with 10 exercise types
-
pronounce-mcpgithub.com/MahammadNuriyev62/pronounce-mcpupdated this year
MCP App with inline audio buttons for word pronunciation and language learning
-
Learn the Greek hiding in everyday English, in 3-minute lessons. Web app + MCP server so your AI agent can tutor you.
MIT ★ 4 -
MCP server for Vocabit — let an AI assistant build flashcard sets inside a real language-learning app and read back how the learner actually did.
npm MIT -
MCP server for Vocabit: an AI assistant builds a flashcard set inside a real language-learning app, then reads back how the learner actually did. Ships with a no-backend demo mode.
MIT -
Unofficial Node.js SDK, CLI, MCP server and Agent Skill for the anton.app learning platform
npm MIT ★ 4 -
Very very very simple MCP server to learn MCPs. It provides AI apps w access to real economic data from World Bank Indicators API.
-
Local-first course context for your AI app: sync your courses, serve them over MCP to Claude / ChatGPT / Codex. Read-only, learning-first.
Apache-2.0 -
Any interface, compiled for a small model. Meta's frontier models learn an app once; a small open model runs it on your computer, every step checked, as a tool any agent can call over MCP.
Apache-2.0 -
Less time on rig chores, more time flying and racing. A free Windows app for flight and racing sim rigs: set up your controls and screens, learn what every button does, get everything running before you launch, and put your desk back after.
MIT ★ 1 -
mcpno update data
Read-only affiliate attribution and commission data for **iOS apps (StoreKit 2)** and **Shopify stores**. Attribloom attributes App Store subscriptions to the affiliate who drove them using the StoreKit 2 `appAccountToken` plus App Store Server Notifications v2, with no device fingerprinting. This server lets an agent read your campaigns, conversions, matured commissions, and payout eligibility. **Two of the seven tools need no API key**, so an agent can learn the integration before you have an account: | Tool | Needs a key | | --- | --- | | `get_started_guidance` | no | | `connect_store_guidance` | no | | `whoami` | yes | | `list_campaigns` | yes | | `campaign_readout` | yes | | `list_payouts` | yes | | `payout_eligibility` | yes | Money mutations (approving affiliates, creating campaigns, approving payouts) are deliberately not exposed. This server is read-only by design, and every figure it returns is read from the real ledger. Get an API key from the Attribloom dashboard under Settings, then API keys.
smithery -
**Persistent memory for AI agents that you can actually read.** Kybase stores what your agent learns as plain Markdown notes with `[[wikilinks]]`, searched by keyword and by meaning. It runs locally: notes live in an embedded Postgres on your machine (`~/.kybase`), with no Docker, no server and no account. **What your agent gets (18 tools)** - **Search** — `search_notes`: hybrid keyword + semantic search that returns the section each excerpt came from - **Read** — `get_note` (whole, windowed or one section), `list_notes`, `list_tags`, `list_folders`, `indexing_status` - **Write safely** — `create_note`, `append_to_note`, `replace_in_note`, `update_note` with conflict protection, `delete_note` / `restore_note` (trash) - **Link** — `get_backlinks`, `get_neighbors`, `get_graph` over the wikilink graph - **Organize** — `create_folder`, `update_folder`, `delete_folder` **Setup** Keyword search works right away. For search by meaning, pick an embedding provider in the settings: local **Ollama** (`ollama pull embeddinggemma`) keeps everything on your machine; **Google** or **OpenAI** need an API key and send note text to that provider. **Your data stays yours** `kybase-mcp export vault.zip` writes every note out as plain Markdown, folders as directories, readable in any editor, Obsidian included. **Want a UI?** The full Kybase app adds a web editor, a knowledge-graph view, share links, and one memory shared by Claude Code, claude.ai and Cursor: [github.com/Kyrzin/kybase](https://github.com/Kyrzin/kybase) Open source, AGPL-3.0.
smithery -
Local study assistant for D2L Brightspace: read-only MCP server, course sync, deadlines dashboard, and Outlook email triage.
★ 2 -
An agent-native teaching OS — a classroom that remembers, for you and your AI. MCP server + self-hosted web app.
AGPL-3.0 ★ 3 -
Free, open-source AI tutor for your classes. Claude Code, Codex or any MCP app teaches you step by step, tracks what you know in a knowledge graph, and preps you for exams. No API keys. Mac, Windows, Linux.
AGPL-3.0 ★ 17 -
MCP server that draws structures, reactions, mechanisms, peptides and proteins for Claude. Structures are drawn locally with RDKit; names, data sheets and proteins are looked up online.
pypi Apache-2.0 ★ 32 -
Graded coding exercises inside Claude. Hidden tests decide pass/fail, and a failed attempt goes back into the chat so the tutor explains your specific mistake. Python, JavaScript, TypeScript and SQL, all run in the browser.
MIT -
Graded coding exercises inside a chat. The assistant writes the lesson and the hidden tests, the widget runs them in the browser, and a failed attempt goes back into the conversation so the tutor explains your specific mistake. Python, JavaScript, TypeScr
npm MIT -
mcp-macgithub.com/samicokar/mcp-macupdated this year
A Proof of Concept MCP server for macOS, enabling AI agents to interact with macOS apps
MIT ★ 1 -
Rigour's MCP server: lets coding agents review their change, check for an existing helper before writing a new one, and recall the team's lessons. Works with Claude Code, Cursor and other MCP clients.
npm MIT -
Docs for Lexpad's remote MCP server: your vocabulary notebook in ChatGPT, Claude and other MCP apps (OAuth 2.1)
-
mac-pilot-mcpgithub.com/leesgit/mac-pilot-mcpupdated this year
Sandbox-protected macOS automation MCP server with a persistent recipe DB, Electron CDP fallback, and self-correcting per-app knowledge
npm MIT -
roampalgithub.com/roampal-ai/roampalupdated this year
Memory that learns what works.
NOASSERTION ★ 126 -
Enable AI to interact with Windows apps by viewing screens, reading UI, clicking, typing, and automating tasks with OCR and window detection.
MIT ★ 5 -
A powerful, AI-driven blockchain explorer powered by specialized Pydantic agents. This project uses a FastMCP server to expose tools for querying chain data, analyzing accounts, and checking transaction statuses directly within the Claude Desktop app, including complex cross-agent analytical workflows.
MIT ★ 1 -
AI computer use for the whole Mac, with any AI: Claude, ChatGPT, Gemini, OpenRouter or a local model. A native MCP server, a menu bar agent that learns shareable skills, and benchmarks you can run on your own model. No API key needed through MCP.
★ 4