Claude Desktop インストールガイド
ローカル MCP 設定に対応するデスクトップクライアント。
MCP Servers

Define TypeScript capabilities that send emails, manage calendars, and automate work. Expose them to the Routecraft agent, Claude, ChatGPT, Cursor, or any AI agent via MCP.

Unofficial Relace MCP client with AI features. Personal project; not affiliated with or endorsed by Relace

A FastMCP server implementation for the Semantic Scholar API, providing comprehensive access to academic paper data, author information, and citation networks.

A MCP server to connect to wolfram alpha API.

This server interacts with the Unstructured API to manage sources, destinations, and workflows. It is not actively maintained and is kept here for reference.

Whole-codebase knowledge for AI coding agents. A field-aware code graph (functions, classes, methods, fields, references) plus persistent memory. Rust, Postgres + pgvector, MCP.

An MCP server for getting AWS spend data via Cost Explorer and Amazon Bedrock usage data via Model invocation logs in Amazon Cloud Watch through Anthropic's MCP (Model Control Protocol).

- - Comprehensive tool documentation with real-world examples - - Data handling and privacy information - - Comprehensive Docker deployment, multi-architecture builds, and production setup

This repo exposes the TMF620 command layer through two interfaces:

Official Sarvam MCP server. Exposes every public Sarvam API — STT, TTS, Translate, Transliterate, Language ID, Text Analytics, LLM (30B / 105B), Vision Document Intelligence, Pronunciation...

This project contains MCP Servers for IBM Cloud which provide an interface layer between AI assistants and IBM Cloud services.

Gives Goose/Cursor access to your iOS/macOS project index through the Model Control Protocol (MCP) and IndexStoreDB.
Agent Skills

Vite plugin that reimplements the Next.js API surface — deploy anywhere

GLM-5.3-Flash × J-Space capability realization — benchmark presentation of the J-Space Cognition Suite

Turn the object in an attached image into a quality-gated, animation-ready procedural Three.js model built entirely with code.

A practical, visual-first guide to comparing AI agents, platforms, runtimes, and orchestration tools so you can shortlist the right options faster.

Reverse-engineered the official API for Jimeng/Dreamina’s text-to-image and image-to-image features. Drew inspiration from several experts’ projects and made some tweaks, which significantly improved...

MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.

飞鼠格式 FlyingMouse Format - Windows 免费文件格式转换工具(离线可用,内置 FFmpeg/LibreOffice/Poppler/Tesseract)。图片/文档/表格/PPT/PDF/音视频/WPS 格式互转 + OCR + 批量转换;音频仅支持普通格式。作者:牢蜂(LaoFeng)|仅供个人免费使用,禁止商业售卖/转卖/套壳

OpenUI is a full-stack, renderer-agnostic Generative UI framework built around a compact, streaming-first language.

AI Edge Gallery is the premier destination for running the world's most powerful open-source Large Language Models (LLMs) on your mobile device.

A Super AI Lab with massive AI Doctors as Assistants. Best IDE for Research via AI Power.

Dinero.js lets you create, calculate, and format money safely in JavaScript and TypeScript. dinerojs.com

[//]: # (These images are referenced by full URLs to ensure they render correctly on https://pypi.org/project/git-machete/) [//]: # (In fact, only the light-mode image is used in PyPI, the other one...