Claude Desktop Руководство установки
Десктопный клиент с поддержкой локальной конфигурации MCP.
MCP Servers
MCP security testing framework for evaluating Model Context Protocol server vulnerabilities
MCP is a command-line tool and local UI for discovering, installing and managing Model Context Protocol servers.
Emacs Lisp implementation of the Model Context Protocol
Continuously updated catalogue of open-source OSINT tools, skills, plugins, MCP servers, and agentic integrations.
Connect Claude.ai to Twitter/X — without paying $100/month for the official API.
This project is in its early stages, and the README is currently minimal.
Model Context Protocol servers you can actually run yourself.
Teamwork.com MCP server
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.
An MCP (Model Context Protocol) server that provides access to Rust documentation from docs.rs. This server allows AI tools to search for documentation, type information, feature flags, version...
One governed graph for AI agents — GraphQL + MCP over your databases, files, APIs, and code
A comprehensive stdio MCP (Model Context Protocol) server for SEO APIs. This server allows LLMs (Large Language Models) to interact with DataForSEO API functions and other SEO tools.
Agent Skills
把 Taiji / TAAC 训练与评估平台变成任何人和任何 agent 都能读取、比较、归档、提交训练、发布模型和收集线上评估证据的实验命令行工具。
An open agentic prompt-expansion harness for image and video generation. Turn everyday intent into validated, model-ready prompts through a bounded AI-agent workflow.
Podcast to Course 专治这种「听过 ≈ 学会」的错觉：它把播客变成**，让洞见不再从左耳朵进、右耳朵拿着离职证明出去。
A Claude skill that checks whether your idea already exists before you build it.
✨ - Type #snippet anywhere in your message and watch it transform.
Drop in a PNG, JPEG or BMP. Get back SVG, EPS, DXF, PDF or PNG. No account, no credits, no subscription. Offline by default.
同一個問題，多幾種看法。涵蓋十大領域的思考輔助 skill，幫你換角度理解問題、找出其他解釋與選項，並檢查成立條件。適用於 ChatGPT、Claude 與 Codex。
The is an open standard that defines what "AI-ready" actually means — six factors, 62 measurable requirements, and five workload profiles that apply to any data platform.
基于 huobao-drama 参考设计，使用 Next.js 16 + 多AI供应商架构 构建。
First human cognitive framework integrated into an LLM. Claude learns to detect if you're assessing, deciding, or doing—and responds appropriately.
AI가 쓴 한국어 초안을 한 사람의 실제 문체로 재작성하는 Claude Code 스킬입니다. 문체를 느낌이 아니라 측정값으로 다루죠
Don't make LLMs honest. Make every factual claim auditable. Do not gag the model. Strip its hallucinations sentence by sentence.