Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
Transparent MCP proxy that reduces the token cost of large upstream tool responses for nearly every other MCP server imaginable.
An MCP server for Basecamp 3. It lets MCP-capable clients such as Codex, Cursor, and Claude Desktop read and manage Basecamp projects through OAuth-authenticated Basecamp API calls.
An MCP server that queries public SearXNG instances, parsing HTML contents into a JSON result
Your AI assistant now remembers everything. Forever. Across every conversation.
The ngrok alternative with .local domains, a scriptable CLI, and an MCP server for AI agents
Testing and evaluation platform to chat, inspect, and debug MCP servers, MCP apps, and ChatGPT apps.
ChatSpatial replaces ad-hoc LLM code generation with . Instead of generating arbitrary scripts, the LLM selects tools and parameters from a curated registry, making spatial transcriptomics workflows...
Git-native API client with encrypted secrets.
Streamable HTTP MCP server for Claude.ai custom connectors.
移动端 AI 自动化测试平台 —— MCP 工具 + AI Agent + 可视化操控台
A modular MCP server providing AI-driven vulnerability management skills, including severity classification and automated insights.
WinDbg extension + Python MCP server. Lets MCP‑compatible clients (Cursor, Claude, VS Code + Cline/Roo) drive WinDbg with clean, validated commands. Kernel‑first; user‑mode works too.
Agent Skills
Grounded in 50+ peer-reviewed sources through April 2026.
Search, monitor, analyze, and export X data from the terminal.
大 QMT 运行环境里的 RPC 桥接包：把大 QMT 内置 Python（行情查询、交易、持仓）封装成**，并兼容一组 MiniQMT 方法名，让外部程序无需 XtQuantServer 权限就能驱动大 QMT。
Generate original print-style for articles and blogs, starring a recurring mascot that performs each idea.
is an agentic harness for writing machine-learning and AI in LaTeX. You give your coding agent a topic, and the harness drives it through a disciplined pipeline: literature discovery, a human...
OpenBKN is an ontology-driven business knowledge network platform. Through ontology modeling, it turns the data and logic scattered across documents, systems, processes, rules, and expert experience...
are modular packages of instructions, resources, and scripts that teach an agent to handle a specialized task. On disk, a skill is just a folder: a SKILL.
Forge Nature-level scientific panels into executable plotting code. Retrieve open-access papers, split full figures into reviewed panels, classify them with Qwen, and reproduce statistical panels...
CLI for the Google Health API v4 — built for AI agents and developers.
Readable RTL → clear behavior → reviewable delivery Give AI the design intent, review the behavior preview, and receive artifacts you can inspect and verify.
Portable for writing ML/AI academic papers — from topic to compiled PDF, with verified BibTeX citations, gated workflows, and multi-agent collaboration.
Perforated is a data-efficiency layer for machine learning that adds artificial to your neural network.