The Model Context Protocol (MCP) is a standardized way to supply context to large language models (LLMs). Using the MCP Python SDK, you can build servers that expose data (resources), functionality (tools), and interaction templates (prompts) to LLM applications in a secure and modular fashion. In this tutorial, we’ll build a simple MCP server in P

Model Context Protocol SDK for Clojure

Best practice website

MCP host app w/ textual user interface, in Python

This project is an arXiv paper retrieval and search service implemented through a custom MCP (Multi-Capability Provider) framework. It provides a server-side implementation to fetch, search, and analyze academic papers from arXiv.org.

MCP Server for interacting with LogSeq graph

letsbonk_mcp_server

An MCP for Day One Journal users.

Model Context Protocol (mcp) server for Miro

base builder mcp

Branch-Thinking MCP Tool A TypeScript-powered MCP server for managing parallel branches of thought, semantic cross-references, and persistent tasks. Features dynamic scoring, AI-generated insights, batch operations, and visual graph navigation for advanced agentic workflows.

Yellhorn offers MCP tools to publish detailed workplans as GitHub issues with entire-codebase reasoning and to review diffs against them

MCP server that provide tools to LLMs such as claude in cursor to interact with MongoDB

Delivers Julia documentation and source access with built-in caching and robust Julia-specific error handling for Claude Desktop.

DynamoDB table and index management, throughput tuning, and CRUD operations with safe-delete safeguards.

AI-driven code analysis, automated code collection, and documentation generation via OpenAI APIs with an easy npx-based setup for rapid, collaborative workflows.

Controls Philips Hue lights and sends Morse code messages via MCP, with local and optional remote API support for Cursor/Claude Desktop.

A Model Context Protocol (MCP) server implementation for Gumroad API

Monad MCP Tutorial

Notion API exposed as actionable tools for LLMs to read, create, update, and delete content seamlessly via natural language guidance and intents.

A MCP Filesystem implementation for Claude, written mostly by Claude

Captures macOS window screenshots, lists windows, and simulates keystrokes for desktop automation and testing.

Seamless, leak-free secret handling with OS keychain or hidden-file storage for IDE-integrated AI contexts.

Framework to annotate React components with semantic metadata and generate a build-time toolchain for AI agents. It keeps component behavior unchanged while exposing machine-readable descriptions that enable AI systems to understand, navigate, and leverage UI elements across projects in a scalable, developer-friendly way.