Claude Desktop Руководство установки
Десктопный клиент с поддержкой локальной конфигурации MCP.
MCP Servers
AI Code Mode extension for Cocos Creator featuring UTCP Server with MCP wrapper
AI MCP for Development with Bedrock, Acorn, Sage.
Commands · MCP Servers · Plugins · Tools · Workflows · Agent Frameworks
A monorepo of Unraid tooling: two MCP servers (Python and Rust) and three Unraid OS plugins, plus the Claude/Codex agent integrations that surface them.
Garmin Connect MCP server based on garth.
A Machine Conversation Protocol (MCP) server that provides Google Contacts functionality, allowing AI assistants to manage contacts, search your organization's directory, and interact with Google...
The only Apple Mail MCP server with — reliable on large mailboxes where AppleScript-based servers timeout. 8 tools for reading, searching, and extracting email content.
Zero trust gateway for MCP servers. Aggregate, filter, and securely access MCP tools from anywhere without VPNs, open ports, or exposed endpoints.
AgentMail has one MCP tool implementation, hosted at:
Offensive security you run yourself — a local MCP workflow for authorized testing, in CI or against staging.
An MCP server that delivers cryptocurrency sentiment analysis to AI agents, leveraging Santiment's aggregated social media and news data to track market mood and detect emerging trends.
PlatformIO MCP is the open-source, agent-first hardware execution layer for embedded development.
Agent Skills
Reusable agent skills for Codex and other Agent Skills compatible tools.
把你在 B 站收藏的访谈/演讲/课程，变成可检索、可追溯来源的**。 适合：访谈/演讲/课程、技术视频与学习视频整理、公开课复盘、知识总结、会议/分享回顾、播客内容归档等。
A collection of reusable skills that give AI Agents expertise in Flux CD, Kubernetes, and GitOps best practices for generating manifests, answering Flux questions, auditing repository structure,...
logo-generator-skill
The Pi extensions and skills I use to keep long agent sessions useful without building a fake operating system around them.
für die anwaltliche Praxis im deutschen Recht – Skills, Sub-Agenten, Workflows etc. als Anregung für Kanzlei-Arbeitsabläufe.
hardhat deployment plugin
⚡️🎉A PyTorch-native Inference Engine with Cache, Parallelism, Quantization and CPU Offload for DiTs
Generate realistic synthetic security logs for cybersecurity threat hunting training and research.
HEY CLI and Agent Skills
A self-improving multi-agent orchestration framework for Claude Code, Gemini CLI, and Codex CLI. Coordinate 18 specialized AI agents and 13 orchestration skills through a complete software...
An open standard for shared agent learning. Agents persist, share, and query collective knowledge so they stop rediscovering the same failures independently.