Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
- 功能集大成：集成市面已有项目的大部分功能，还会继续维护根据issue添加功能 - 依赖极少：只需要一个最新的FastMCP2.0，不需要复杂的uv及特定版本的python - 兼容性强：支持所有MCP功能的大模型助手，无需科学上网配置复杂的依赖和环境，成功率极高 - 代码极简：市面项目大量采用嵌套代码生成工具，可读性极差。本项目浓缩到单文件，mcp.
mcp server for rust code semantic hybrid search bm25 + embeddings with tree-sitter, gpu accelerated indexing and merkle tree updates
locklens 是一个基于 audit-ci 的 lockfile 审计工具，支持三种运行模式：
The MCP gateway is a reverse proxy server that forwards requests from clients to the MCP server or uses all MCP servers under the gateway through a unified portal.
An MCP server that delivers cryptocurrency sentiment analysis to AI agents, leveraging Santiment's aggregated social media and news data to track market mood and detect emerging trends.
MCP Client as Agent Strategy Plugin with Computer Using Agent (UI-TARS-SDK) support. Dify is not MCP Server but MCP Host.
PlatformIO MCP is the open-source, agent-first hardware execution layer for embedded development.
DART API를 활용한 재무 분석 MCP(Model-assisted Capability Package)입니다. Claude를 이용하여 상장 기업의 재무 데이터를 쉽게 분석하고 시각화할 수 있습니다.
Intelligent MCP server for Godot 4. Spatial intelligence, code analysis, and .
Public MCP Server README: capability boundaries, auth, install, and dangerous-tools disclosure.
- — a dedicated adversarial agent attacks the coder's output in a structured loop (createReviewLoop) until it survives review or is rejected; consensus checkpoints and per-agent resource limits keep...
Datadog's managed MCP server connects your AI agents to Datadog's observability tools and data. Query logs, metrics, traces, incidents, and more - directly from your AI-powered dev tools.
Agent Skills
Academic Research Skills for Claude Code: research → write → review → revise → finalize
🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman
Structured multi-perspective deliberation for decisions that deserve more than one reasoning path.
Matt Shumer's aim prompt as a slash command — build a game against a named reference. Fill the three paragraphs. Run them. Stop when you stop it.
817 structured cybersecurity skills for AI agents · Mapped to 6 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND, NIST AI RMF & MITRE F3 (Fight Fraud) · agentskills.
Browser Harness | Self-healing harness that enables LLMs to complete any task.
이 저장소는 hugohe3/ppt-master(MIT)를 기반으로 한 **입니다. 한국어 덱 제작에 맞춰 작업 절차 커스터마이징, 완료 PPTX 검증 워크플로우) 등이 조정·추가되어 있습니다. 원 프로젝트의 라이선스와 저작권 고지는 그대로 유지합니다.
An agentic skills framework & software development methodology that works.
Convert documentation websites, GitHub repositories, and PDFs into Claude AI skills with automatic conflict detection
Multi-agent AI development templates for opencode
We are moving from "prompt as text" to . Each skill acts like a lightweight, containerized application for AI work: a stable interface, opinionated workflow, and bundled resources that can be...
A Claude Code skill that consolidates scattered project markdown files into a single canonical CLAUDE.md, with a pinned PROGRESS block at the top.