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
A Model Context Protocol (MCP) server for category-aware web search, website scraping, and date/time tools. Designed for seamless integration with SearXNG and modern MCP clients.
A Model Context Protocol (MCP) server that enables AI assistants to interact with Slack workspaces. This server provides a bridge between AI tools and Slack, allowing you to read messages, post...
A gateway for Model Context Protocol (MCP) servers.
The dicom-mcp server enables AI assistants to query, read, and move data on DICOM servers (PACS, VNA, etc.).
is a lightweight server that can run and manage multiple Model Context Protocol (MCP) servers, specifically designed to integrate with TypingMind.
𝔐 mpc-openai ✧ MCP Client with OpenAI compatible API
Remote control AI coding assistants (Claude Code/Codex) via Telegram
A Model Context Protocol (MCP) server that provides programmatic control over iOS simulators. This server implements the MCP specification to expose simulator functionality through a standardized...
A Model Context Protocol (MCP) server that provides access to the Oura API. It allows language models to query sleep, readiness, and resilience data from Oura API.
Retrieval-augmented search, hooks, and an MCP server in a single local system. No API keys, no cloud dependencies.
The Gemini CLI confirmed that the MCP server built with Google Apps Script (GAS), a low-code platform, offers immense possibilities.
Core PHP implementation for the Model Context Protocol (MCP) Client
Agent Skills
🚀 OpenManus-Max An Advanced Autonomous AI Agent Framework with Multi-Level Permissions & Trust Attenuation
A flexible and powerful AI agent library for Python, designed to build agents with tool support, multimodal capabilities, and streaming responses.
A collection of advanced agentic tools, skills, and workflows designed for the Antigravity AI coding assistant.
面向中文用户的 。项目基于 learn-claude-code 的 Agent 工程思路改造，用 Python + Aliyun DashScope/Qwen 实现一个只读 PR Review Agent：读取 Git diff 和 PR 描述，组织多个 reviewer 生成候选问题，再通过 debate loop 对 finding...
- : write in rich text or raw Markdown, switch anytime - : fully Obsidian-compatible - : a daily capture stream for quick notes, accessible from anywhere - inspired by Raycast: find anything as you...
A tiny skill that surfaces relevant terms of art as you work with agents, growing your domain vocabulary over time
一个可开新档的 AI 健身教练框架：训练记录、RPG 属性成长、剧情推进三者联动
A Swift library for macOS automation — mouse, keyboard, screenshots, image recognition, and AI-powered agents.
macOS 可用 · Windows beta · DeepSeek API key · 非商业使用 English README
只需要一句指令，就能让 Codex 把 GPT Image 2 生成的美观图片转换为 PPTX；然后在 PowerPoint 中选择**或**，即可编辑重建后的各个元素。注意， 如果要编辑比较底层的元素可能需要多次的**，因为我们的重建逻辑涉及多层次的 元素组合。
adds rollback/recovery, adaptive context loading, and model routing intelligence on top of the original GSD by TÂCHES. Synced with upstream v1.24.0.
PhD students spend weeks on literature surveys. Most of that time is plumbing — finding papers, extracting claims, cross-referencing terminology, building comparison tables, chasing citation chains.