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

База знаний по zapret2 (DPI bypass) и blockcheckw (сканер стратегий). Работает как MCP-сервер для LLM-агентов и как обычная документация.

@cyanheads/mcp-ts-core Agent-native TypeScript framework for building MCP servers. Build tools, not infrastructure.

MCP server for Selver.ee product search and cart management. Pairs with chrome-devtools-mcp to open the cart in a real browser for checkout.

A Multi Agent Memory MCP That Connect Agents Across Systems and Machines

MCP server for Unreal Engine that uses Unreal Python Remote Execution

MCP Observatory is the CI-native security tool for teams shipping custom MCP servers. Test during development, catch schema drift, simulate attacks, and generate compliance evidence — before agents...

Custom multi-agent system, no LangChain · public evals with the weak scores kept in · live in production

A drop-in replacement for fsi.exe that adds MCP capabilities to F# Interactive sessions. Perfect for AI-assisted development workflows where you need programmatic access to F# Interactive.

Local-first persistent memory and project knowledge runtime for coding agents.

Community-maintained MCP server for Wireshark / tshark. Not affiliated with Wireshark or Anthropic. Give your AI assistant direct access to packet captures. Ask Claude to summarize a .

MCP server that gives AI agents the ability to execute cross-chain cryptocurrency swaps and transfers via the deBridge protocol

MCP server for Cosense (formerly Scrapbox).
Agent Skills

MicroCodex is an ultra-lightweight coding agent that runs in your terminal

audit-prompt-caching is a portable Codex/agent skill for finding why LLM cache reuse fails across the request path: prompt/prefix caches, provider cache telemetry, cache-aware routing, agent tool...

Private skill catalog / marketplace for teams

Turn one human UI page flow into reusable automation capabilities, then assemble new testing flows from those capabilities instead of recording everything again.

Review reconstructed geometry and generated CAD documents before using this version in production.

Trust nothing. Ship safely. — Skeptical-reading and prompt-injection defense skill for AI agents. Provenance tagging, red-flag patterns, refusal templates, and a read-only injection auditor. MIT.

VS Code-style typewriter animation video skill for AI agents (agentskills.io format)

Front-End Checklist is the open-source front-end quality system for humans and AI agents. It turns front-end best practices into a practical review workflow you can browse on the web, run through...

Minimal faithful re-implementation of Microsoft SkillOpt: a text-space optimizer that trains a deployable natural-language skill for a frozen LLM agent on HotpotQA.

本地零成本会议 / 面试录音转录 + AI 智能清洗工作流。告别飞书妙计 / 通义听悟,30 分钟录音直接出 Markdown 或 Word,给 AI agent 一句话就能跑完。

The marketplace where your Skills earn for you — publish a Skill you built and get paid every time someone runs it, closed-source. You can also use Skills built by real industry experts.

114 MIT-licensed agent skills for Claude Code and every agentic runtime: MCP, Next.js, Oracle Cloud, Suno, code review. The full FrankX catalog.