Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
YAMCP (YAM-C-P) is a command-line tool for organizing and managing MCP servers as local workspaces. It seamlessly connects to multiple MCP servers, local or remote, grouping them into a unified...
A Model Context Protocol (MCP) server that provides comprehensive access to MLB statistics and baseball data through a FastMCP-based interface.
Local-first and static by default — no agent execution, tool calls, LLM calls, or network access.
http4k MCP Desktop Client
A Node.js implementation of the Model Context Protocol (MCP) that provides secure shell command execution capabilities.
Supercharge OCaml development with AI coding agents. This MCP server gives AI assistants deep integration with your OCaml projects through Dune, Merlin, and other OCaml Platform tools.
A Python-based flow for securities analysis using the . The repository bundles market data, parsing, analytics and visualisation tools behind a FastMCP server so that they can be consumed locally or...
Expose your Rails app as an AI accessible interface — define tools and resources the Rails way.
- Add @Tool / @McpTool to every method - Duplicate business logic into a parallel "MCP" code path - Maintain separate tool descriptions
Connect any tool that has a REST API, CLI or SDK to your Claude, Cursor, VS Code, or any other AI Client that supports MCP (Model Context Protocol)
A minimal MCP (Model Context Protocol) server that provides AI assistants with access to bpftrace kernel tracing capabilities.
Official Supadata MCP Server - Adds powerful video & web scraping to Cursor, Claude and any other LLM clients.
Agent Skills
A lean .claude/ setup for daily development. Seven specialist agents, twelve workflow skills, six modular rules, and eight safety/productivity hooks.
A collection of skills for AI financial analysis.
A skill collection for creators who want to streamline writing, X Articles draft publishing, WeChat digital-asset capture, and local workflows with Claude Code and Codex.
This repository contains sample prompts and agent instructions for Microsoft Copilot, GitHub Copilot, and Microsoft 365 Copilot.
本项目把传统术数相关的 AI skill 拆成可审计、可复用、可逐步扩展的工程模块。目标不是把模型包装成“更会玄学”，而是尽量减少它在排盘、流派口径、步骤顺序和解释链路上的幻觉。
Linear Chain-of-Thought anchors on whatever it says first. Tree-of-Thought widens the search but still walks a single shared context, so the anchoring persists across branches.
1. 对话 skill 模式：在聊天中按 SKILL.md 约束执行单轮改写；安装本仓库作为 skill 后即可直接使用。 2. 脚本 API 模式：通过 scripts/run_aigc_round.py 执行单轮分段处理，并按需调用外部 OpenAI 兼容接口。 3. Web 模式：启动本地后端和前端页面，在浏览器中完成上传、配置、执行和导出。 4. app：安装app可直接使用
Expert-level compliance guidance for ISO 27001, SOC 2, FedRAMP, GDPR, HIPAA, NIST CSF, PCI DSS, TSA Cybersecurity, ISO 42001 AI Management System, ISO 27701 Privacy Information Management, DORA...
CAR is a meta-harness for coding agents (Codex, Hermes, OpenCode, OMP, anything ACP). It is not a coding agent itself. You bring the plan and the agents; CAR coordinates the long-running execution.
得到 APP 课程下载工具，可在终端查看文章内容，可生成 PDF，音频文件，markdown 文稿，可下载电子书。可结合 openclaw +skill 等使用
🦀 Crabwalk 🦀 Real-time companion monitor for OpenClaw agents.
Repeatable agents-plus-code workflows, packaged as one skill, stamped into any repo. Deterministic Python owns the graph; coding agents are bounded nodes inside it.