#mac

MCP server for interacting with iMessage on macOS

Mirror of

MCP server for macOS text-to-speech functionality

Mirror of

(by marcusschiesser) - Integrate the data stored in a managed index on LlamaCloud

Mirror of

MCP server for accessing geologic data with the Macrostrat API

A server for managing contextual data in DICOM tools, supporting medical imaging and machine learning workflows.

MCP server for stata do file

An MCP (Model Context Protocol) server for executing macOS terminal commands with ZSH shell. This server provides a secure way to execute shell commands with built-in whitelisting and approval mechanisms.

An MCP Server exposing open Emacs buffers as Resources

This SDK provides a Go implementation of the Machine Control Protocol (MCP), enabling bidirectional communication between clients and servers for tool execution, resource access, and prompt handling. Based on

Mirror of

Native Mac Use for LLMs and MCP Servers.

A Model Context Protocol (MCP) server that provides notifications for Claude Desktop on macOS. It plays configurable system sounds when Claude completes a task, enhancing user experience by eliminating the need for constant visual monitoring.

Turn slow PyTorch into fast CUDA/Triton kernels. 32 parallel swarm agents optimize your code on real datacenter GPUs (B200, H200, H100, A100) with up to 14x speedup over torch.compile.

Super Shell MCP

Uses Claude or OpenAI API to convert prompt-mapped input into concrete MCP server components such as tools, resource templates, and prompt handlers.

MCP server for training Linear Regression Model.

A minimal agentic app to interact with OLLAMA models leveraging multiple MCP server tools using BeeAI framework.

sharing what I've learned with mcp servers on mac os x.

Model Context Protocol (MCP) with Gemini 2.5 Pro. Convert conversational queries into flight searches using Gemini's function calling capabilities and MCP's flight search tools

MindManager MCP Server for Automation and Integration on Win + macOS

KinielaGPT es un servidor MCP (Model Context Protocol) diseñado para potenciar tus predicciones de la Quiniela mediante un análisis avanzado de datos. Combina las probabilidades oficiales de LAE con un análisis contextual profundo: histórico de enfrentamientos, rachas recientes, clasificación y rendimiento como local o visitante. Ofrece tres estrategias de predicción, detección de sorpresas y un análisis pormenorizado partido a partido.

A lightweight MCP server that integrates with Apple Notes to create a personal memory system for AI. Easily recall and save information from your Mac using simple AppleScript commands. Compatible with all macOS versions with minimal setup requirements.

Glutamate is a powerful desktop platform that simplifies the deployment and management of Model Context Protocol servers. It provides a user-friendly interface and robust tools for server administration, making it easier than ever to run and customize your MCP servers.

BoltAI is an all-in-one AI chat client. It supports MCP tools calling, dynamic MCP server management and in-context server control. Key features: - Multiple AI providers & models - MCP server integration - Native app: fast & powerful - Import configuration from Claude or Cursor - Built-in configuration editor

Analyzes user-described build features (e.g. database, API integration, tools) and extracts core server requirements like resources, tools, prompts, external systems, and transports needed for MCP.

A macOS AppleScript MCP server

Model Context Protocol (MCP) with Gemini 2.5 Pro. Convert conversational queries into flight searches using Gemini's function calling capabilities and MCP's flight search tools

Let AI agents like ChatGPT & Claude use real-world local/remote tools you approve via browser extension + optional MCP server

Final unified interface for global users. Just describe your server, paste your API key (Claude/OpenAI/Grok), and this library will build, test, and deploy the full MCP server locally or remotely.

A Model Context Protocol (MCP) server for agentic retrieval of financial data from Yahoo Finance. This server leverages YFinance to provide a simple and efficient way to access historical stock prices, dividends, stock splits, company information, and other financial metrics. This MCP server is designed to be used with various LLM applications that support the Model Context Protocol, such as Claude Desktop and Cursor. It allows users to retrieve financial data in a structured way, making it easy to integrate into AI applications.

A Model Context Protocol (MCP) server for agentic retrieval and semantic search over unstructured and structured data using Milvus, a high-performance vector database. This server enables large language model (LLM) applications to efficiently index, store, and retrieve vector embeddings derived from diverse data sources—such as documents, images, metadata, or logs. By leveraging Milvus, the MCP server supports similarity search and contextual retrieval, enabling intelligent access to relevant information based on natural language queries. Designed for integration with MCP-compatible clients, this solution provides a scalable, low-latency foundation for building AI-powered applications with contextual awareness and retrieval-augmented generation (RAG) capabilities.

MCP server that execute applescript giving you full control of your Mac

A iOS/MacOS Swift MCP Client using voice interacting with python MCP servers both natively

## What Peekaboo Can Do Peekaboo provides three main tools that give AI agents visual capabilities: - **`image`** - Capture screenshots of screens or specific applications - **`analyze`** - Ask AI questions about captured images using vision models - **`list`** - Enumerate available screens and windows for targeted captures Each tool is designed to be powerful and flexible. The most powerful feature is visual question answering - agents can ask questions about screenshots like "What do you see in this window?" or "Is the submit button visible?" and get accurate answers. This saves context space since asking specific questions is much more efficient than returning raw image data. Peekaboo supports both cloud and local vision models, letting you choose between accuracy and privacy.

Digimon Engine — Multi-Agent, Multi-Player Framework for AI-Native Games and Agentic Metaverse

A zero-installation solution for AI agents to control remote macOS systems. Full desktop capabilities without extra software, using only built-in Screen Sharing. Works with Claude and any MCP client, offering native macOS experience with minimal setup and no additional API costs.

Automatically generates a full MCP server codebase (Node/Python/Java) using the validated schema, outputting modular files for CLI-based execution or Claude Desktop connection.

CLI tool to scaffold, run, and test MCP servers locally with Node.js or Python, integrated with Claude and OpenAI key injection and auto-link to Claude Desktop.

MacPilot CLI is a mcp server, It provides a collection of system tools that allow AI assistants to perform various operations on macOS systems.

MCP Server for Last.FM APIs, built in Swift