Claude Desktop Руководство установки
Десктопный клиент с поддержкой локальной конфигурации MCP.
MCP Servers
A Middy middleware for Model Context Protocol (MCP) server integration with AWS Lambda functions.
This is a 12306 ticket search server based on the Model Context Protocol (MCP).
![GitHub Release][releases] ![GitHub Activity][commits]  ![HACS][hacs] ![BuyMeCoffee][buymecoffee]
A desktop MCP client designed as a tool unitary utility integration, accelerating AI adoption through the Model Context Protocol (MCP) and enabling cross-vendor LLM API orchestration.
Cesium AI Integrations is a collection of reference integrations, experiments, and patterns that connect the Cesium ecosystem with AI systems such as LLMs, retrieval pipelines, and agent workflows.
The official draw.io MCP (Model Context Protocol) server that enables LLMs to create and open diagrams in the draw.io editor.
The Extension is open-source and at https://github.com/jasonkneen/mcpz-vscode and in the mcspx-tweaks branch
MCP security testing framework for evaluating Model Context Protocol server vulnerabilities
Use Breakcold as a remote Model Context Protocol server from AI tools such as Claude, ChatGPT, Codex, OpenClaw, Hermes, TypingMind, LM Studio, LibreChat, and Microsoft 365 Copilot.
This project is in its early stages, and the README is currently minimal.
Open-source desktop SQL workspace for PostgreSQL, MySQL/MariaDB, SQLite and 15+ more databases like DuckDB, ClickHouse, Redis and Firestore.
A simple, locally hosted Web Search MCP server for use with Local LLMs
Agent Skills
Fast, powerful Markdown formatter for agents with smart typography and advanced features
A statistically-sound agentic loop-engineering framework. You give it a task description, a pile of gold-standard input/output examples, and a set of checks; it runs agentic loops (a strategy agent...
YuE2: frontier music generation with symbolic planning, zero-shot covers, and agentic music editing.
AI-assisted tools for building, testing, and deploying Fivetran Connector SDK connectors. Distributed as a native plugin/extension for Claude Code, Codex CLI, Gemini CLI and GitHub Copilot CLI.
Lore injection: how fabricated memory becomes model trust
A portable Agent Skill for AI product engineering + open-source maintainer intelligence . Map the repo. Route the task. Review risk. Prepare releases. Harden automation. Prove the result.
Stop TODO leftovers, leaked secrets, sloppy commits and red CI from reaching main — with zero review bandwidth spent on the obvious stuff.
Draft Proposal (see CHANGELOG.md for version history)
它会根据角色参考图、服装参考图、场景参考图、人物关系、剧情想法和目标时长，生成更适合视频模型直接执行的完整提示词，重点处理人物一致性、情侣 POV、自然对白、微表情、手部互动、镜头连续性与真实生活感。
A complete agentic pipeline to kill a SaaS: pick a target, cut the 20% that matters, rebuild it on your boilerplate, ship it to production. One method = a suite of commands.
The system of action for AI-native cybersecurity—where intent becomes governed execution, evidence becomes operational memory, and every operation improves the next.
Write the feature. Do not build a bank around it. 写一个功能就写功能，不要在它外面修一座银行金库。