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
AI-native ontology engine: a Rust MCP server with tools for building, validating, querying, and reasoning over RDF/OWL ontologies.
Phone numbers as tools. Your agent orders a private number in the country a service expects, reads the SMS verification code straight from the API, and hands the number back.
Everything I've found that actually makes Claude Code output better-looking frontends. Skills, plugins, MCP servers, CLAUDE.md tricks, organized by what you're trying to do.
Your agents forget everything between sessions. MemMesh gives them durable, typed, searchable memory that lives on your machine — no vector database, no search cluster, no mandatory LLM calls.
Vite plugin that enables a MCP server helping models to understand your Vue app better.
Vestige is a local-first memory for AI agents that reaches backward through time to find the quiet change that caused today's failure: the cause that looks nothing like the bug. One 23MB Rust binary.
Multi-instance IDA Pro MCP server — analyze multiple binaries simultaneously through a single MCP endpoint.
Most MCP integrations for Unreal register every action as a separate tool. That floods the AI's context window with hundreds of tool names before you've asked a single question — and the actually...
An Obsidian-native memory layer for your AI agent. Plain Markdown you own, in the same vault you already use.
mcp-context-protector is a security wrapper for MCP servers that addresses risks associated with running untrusted MCP servers, including line jumping, unexpected server configuration changes, and...
A reasoning implementation for Claude Desktop that lets you use both Beam Search and Monte Carlo Tree Search (MCTS).
A universal, all-in-one MCP server that brings the full power of the Universal Tool Calling Protocol (UTCP) to the MCP ecosystem.
Agent Skills
Speedily search and merge log messages by datetime
Набор скиллов для работы с 1С:Элемент для AI агентов
这里放的是我希望 Agent 长期带着走的工作流：能触发、能执行、能验证、能复用，而非临时 prompt 或一次性脚本。
Reduce hallucinations through first-principles reasoning, verification, self-critique, and explicit uncertainty for AI agents.
Sign in with Agent
Build production-ready AI agents in Claude Code from natural language. Analyzes your problem, researches best practices, and generates subagents, skills, hooks, commands & MCP configs.
Slides AI Plugin for Claude, OpenClaw, etc that turns any idea into a full presentation — animated HTML or editable PowerPoint — from a single prompt
Comprehensive Java code health analyzer that scans for security, performance, correctness, and architecture issues. Outputs a 0-100 score with actionable diagnostics.
Claude Code skill for AI video & image generation via agent-media CLI
Bring Galileo powered eval workflows into Claude Code and Codex.
每个 Skill 是一个 Markdown 文件，被 AI 编程助手（如 Trae、Cursor、Copilot 等）加载后，能够引导 AI 正确完成嵌入式开发任务——从环境搭建、项目创建、编译、烧录到调试，全链路覆盖。
Claude Code Skills collection for BMAD