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 collection of Model Context Protocol (MCP) servers, clients and developer tools by IBM.
A Model Context Protocol (MCP) server for read-only Linux system administration, diagnostics, and troubleshooting on RHEL-based systems.
Nosia is a platform that allows you to run AI models on your own data with complete privacy and control.
tunnel-client is the customer-run agent behind Secure MCP Tunnel. It connects a private or localhost MCP (Model Context Protocol) server to ChatGPT, Codex, the Responses API, and AgentKit through an...
— Security: removed child_process dependency entirely; debug endpoints now require auth; localhost guard on all LS RPC calls. See CHANGELOG.
A comprehensive Model Context Protocol (MCP) server implementing the latest specification.
Build MCP Agents
A comprehensive guide to understanding and building Model Context Protocol (MCP) Servers for C# developers.
Composable AI Agents & Realtime Data Interfaces Powered by Model Context Protocol CA:0x7bfdb47ab24b6cb7017865431179e150d4bc4444
An MCP server implementation that integrates the Brave Search API, providing comprehensive search capabilities including web search, local business search, place search, image search, video search,...
Query CVEs, exploits and advisories enriched with CVSS, EPSS and exploitation status; assess your software, hosts and SBOMs for the vulnerabilities that affect them; and stream the whole graph for...
DeepContext is an MCP server that adds symbol-aware semantic search to Codex CLI, Claude Code, and other agents, giving them more precise context of even the largest codebases.
Agent Skills
This skill makes an AI agent run error analysis on a dataset. Point it at a JSONL/CSV/JSON file of LLM outputs or traces, and it:
Distills Linus Torvalds' code-review methodology from his LKML emails into a reusable, language-agnostic skill.
一套完整的免杀解决方案，涵盖 Shellcode 处理与 Loader 编写，综合运用 Indirect Syscall、ETW 补丁、Module Stomping、字符串加密、IPv4 混淆等技术，用于绕过主流杀软和 EDR 检测。
The Definitive AI Agent Benchmark Standardized, reproducible evaluation across 314 tasks, 33 domains, and 4 difficulty levels.
Skillify watches what you did in a conversation — the tools you used, the corrections you made, the workflow you followed — and captures it as a portable agentskills.io SKILL.md file.
X Tweet Skills for OpenClaw - 推文自动创作技能包
StartupKit is an for Claude Code. It decomposes the business-ideation problem into a bounded sequence of 11 phases — diverge → niche → competitors → positioning → offer → validate → money → leads →...
A rugged, high-quality configuration suite for AI Agents. Getting Started · View Rules & Skills · Request Feature ·
Issue trees, decision memos, McKinsey-style charts, full deck pipelines — the stuff strategists, PMs, and ops leaders run anyway, now executable in one prompt.
: Build Nano Banana Pro Apps 10x Faster (Claude Code Skill) Get it from BuilderPack.ai or just the Claude Code Pack
基于 12+ 媒体深度报道， 结合1143次连麦记录与课程内容分析， 提炼 4 个核心心智模型、7 条决策启发式和完整的表达DNA。
OpenClaw aka (Clawdbot, MoltBot) is an open agent platform that runs on your machine and works from the chat apps you already use.