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
Drain MCP is a FastMCP server that exposes Drain3 log template mining as MCP tools. It can learn templates from individual log lines or whole log files, run read-only inference against the trained...
Let your AI agents actually work as a team. Multi-agent collaboration for Claude Code, Gemini CLI, Codex CLI, Ollama, and API-backed agents — with a live operator dashboard and a 3D virtual office to...
Interactive terminal coding agent in Rust — runs the DeepSeek V4 Flash model locally on macOS (Metal), with a Ratatui TUI, a full tool suite, MCP, and persistent sessions.
Claude Code skills that let Claude interact with ScienceDirect (Elsevier) through Chrome DevTools MCP.
1. Give LLMs the capability of converting source code into AST(Abstract Syntax Tree), regardless of language. 2. One binary should be everything the MCP client needs.
MCP server that exposes the CODESYS V3.5 IDE scripting API as 41 tools and 3 resources, with the CODESYS UI kept open across calls via a file-based IPC watcher.
OrigeneMCP is a core component of the OriGene ecosystem, a self-evolving multi-agent system designed to act as a virtual disease biologist.
A Model Control Protocol (MCP) server that allows Claude to communicate with locally running LLM models via LM Studio.
Plugin-based security tool server via MCP. Each tool is a plugin — all directly callable in a single LLM turn.
MCP server and CLI toolkit for web search and crawling, built on Crawl4AI and SearXNG.
Free trending topics aggregator — 20 sources, zero auth. CLI + Python library + MCP Server.
An MCP server implementation for configuring OpenTelemetry Collectors.
Agent Skills
Open Data, more than 50 financial data. 提供超過 50 個金融資料(台股為主)，每天更新 https://finmind.github.io/
a local gui for managing opencode configurations. toggle mcp servers, edit skills, manage plugins, handle auth - no json editing required.
The CLI for the Claude API
中国科研常用LaTeX模板集
A collection of education skills that turn academic problems into .
skill for explaining architecture
1. ：资料分析分值密度最高，必须先做且做对 2. ：性价比最低，留5-8分钟挑5-7道会做的，其余统一蒙 3. ：会就选，不会就蒙，单题不超过30秒 4. ：做完资料涂一次，做完言语判断涂一次，避免最后来不及
Desktop AI Assistant powered by a multi-provider coding agent runtime
Self-improvement skill for OpenClaw. It captures learnings, errors, and feature requests to support continuous improvement across sessions.
面向 GEO（Generative Engine Optimization）工作流的开源 Skill 仓库。
Notebooks, code samples, sample apps, and other resources that demonstrate how to use, develop and manage machine learning and generative AI workflows using Google Cloud Vertex AI.
Comprehensive Cloudflare platform reference docs for AI/LLM consumption. Covers Workers, Pages, storage (KV, D1, R2), AI (Workers AI, Vectorize, Agents SDK), networking, security, and...