Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers

Citra — PDF answers with page-level proof. Local-first structured text, tables, OCR, visual evidence, and citations via MCP, CLI, and SDK.

一个将ACE(Augment Context Engine) 做成MCP的项目

AgentKit: Build multi-agent networks in TypeScript with deterministic routing and rich tooling via MCP.

MCP Server for Turkish & American Stock Exchange and Fund Data

MCP server to deploy apps to Cloud Run

为 AI Agent 提供统一、可路由、可追溯的多市场金融数据 19 个稳定 MCP Tools · Tushare / Qveris / Binance · stdio + Streamable HTTP

An MCP server for interacting with Sentry via LLMs.

Claude spawning scene objects and controlling their transformations and materials, generating blueprints, functions, variables, adding components, running python scripts etc.

Talk to a Cloudflare Worker from Claude Desktop!

MaverickMCP - Personal Stock Analysis MCP Server

MCP to connect your LLM with Spotify.

Open-source cross-agent memory layer for coding agents via MCP. Compatible with Claude Code, Codex, Cursor, Windsurf, Gemini CLI, Antigravity, OpenClaw, Hermes Agent, Oh-my-Pi, Pi, Copilot, Kiro,...
Agent Skills

OpenCode plugin that automatically downloads and keeps Skills up to date

Terminal UI for NVIDIA Nsight Systems profiles — timeline viewer, kernel navigator, NVTX hierarchy

Connect external AI agents, the existing Sisyphus toolset, and SiYuan's official MCP plugin ecosystem.

Golden inputs, expected constraints, drift table, and CI pseudo-code — catch prompt regressions before ship.

This repository is a reference implementation of the stack on Trac Network for an .

Você herda um .pbix de 400 medidas sem documentação. Gasta 3 semanas só pra entender o modelo. Aí precisa criar uma medida e digita DAX no editor pequenininho do Power BI Desktop.

Skills, plugins & sub-agents Claude Managed Agents multi-agent + custom Skills + the pre-built docx skill 60 minutes A coordinator agent that fans work out to 3-5 specialist sub-agents, each with its...

First human cognitive framework integrated into an LLM. Claude learns to detect if you're assessing, deciding, or doing—and responds appropriately.

Battle-tested execution playbooks that give any AI agent the exact commands, APIs, and patterns it needs — cutting token usage by and making local models as capable as GPT-4.

Distill scam playbooks into AI—see which step you’re on. Defense only. 把骗局套路蒸馏成 AI,看清你在第几步——仅供防范

Describe your workflow in one sentence, and get a complete workflow definition file ready to import into Coze, Dify, or ComfyUI — including node configuration, edges, layout, and all...

One CLI. The whole modern .claude/ surface — settings.json, agents, skills, slash commands, hooks, PRPs — wired correctly the first time.