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

Make your MCP servers secure and production ready

A MCP server for the stock market data API, Alphavantage API.

A browser in the agent's hand. 9 MCP tools, self-diagnosing verdicts, single Go binary.

MCP server to fetch YouTube transcripts

Keeping up with AI trends is exhausting. Claude doesn't know what happened after its training cutoff. Ask it "what's hot in AI right now?" and you get stale answers.

CLI-first semantic code search with MCP integration. Modern, fast, and intelligent code search powered by ChromaDB and AST parsing.

Stdio MCP server for sandboxed file access — read files, search content, safely edit with checksums, and manage file structure.

Secure MCP Gateway - Setup Admin level gateway functionality for MCP servers - with guardrails at each MCP server to overcome multiple security issues with using MCPs

Install and configure MCP servers across all major AI clients with one command.

基于 的增强版本,通过**显著减少对 Figma API 的请求次数,从而缓解速率限制问题,提升稳定性与响应速度。

A specialized MCP server that bridges Neo4j graph database with AI agents, providing memory-focused tools for storing, recalling, and connecting information in a knowledge graph.

Relay beside your IDE — the agent pauses, you review & answer, it continues. All in one tools/call .
Agent Skills

Multi-agent team orchestration skill for Claude Code.

Accounts are free, with a 100 MB storage quota and rate limits sized for agent workloads.

Browser automation agents forget everything between runs. Same site, same page structure to figure out, every single time. Wasted time, wasted tokens.

A Meta-Skill for Private-First Distribution of Agentics (Skills, Agents, and Prompts) across your Agents, Devices, and Teams.

A Claude Code skill for generating Mermaid diagrams. Supports 23 diagram types including flowcharts, sequence diagrams, class diagrams, ER diagrams, Gantt charts, and more.

Crew44 turns the AI agents you already run — Claude Code, Codex, Gemini, Cursor, and more — into a coordinated team.

LLM Wiki 是一种用 LLM 构建个人知识库的方法论。与传统 RAG(每次查询从头检索)不同,LLM 会**,知识随每次导入和查询不断积累,形成复利效应。

输入一个行业,帮你看清钱、权力和机会;输入一家公司,先确认投资或求职目的,再判断它是否值得买、值得去。 🔒 — 所有结构化金融数据(行情/财报/估值/一致预期/研报/资金流向等)均来自腾讯自选股官方数据接口,与微信「腾讯微证券」小程序、腾讯自选股 APP 同源。A 股/港股覆盖深度尤其突出。行业与宏观数据辅以权威一手材料交叉验证,每份报告逐条标注信源等级(A/B/C)。

AutoClaw is a hyper-lightweight AI agent designed to live inside Docker containers. Unlike heavy, GUI-dependent agents, AutoClaw is built for headless, massive-scale concurrency.

*This video was generated by this pipeline — Vietnamese TTS + HyperFrames + GSAP animations, no manual editing.*

Started from a PyMol plugin, towards a comprehensive molecular design assistant.

Production-ready patterns for React Native development, packaged as a Claude Code plugin. Maintained by Software Mansion.