Cursor インストールガイド
開発者向け MCP サーバーとよく使われる AI コードエディタ。
MCP Servers

— Let your AI agent directly control your Gaggimate

The #1 Obsidian MCP for AI memory — freshness-aware, cited, local-first and read-only by default. Dataview, Bases, PDFs, every agent.

Grok Build plugin for Claude Code, Grok, Codex, Cursor and others. Provides /grok:search, /grok:review, /grok:rescue commands + grok_search MCP tool for live X/web search.

Figma MCP build with Rust, server with full read/write access via plugin (no REST API, no rate limits, 73 tools)

Universal database MCP server — give AI assistants read/write access to your databases using connections already saved in your local DB client workspace (DBeaver-compatible).

MCP Audit scans your AI development tools (Claude Desktop, Cursor, VS Code) and reveals:

An MCP server that validates, auto-fixes, and scaffolds TwinCAT 3 XML files. Connect it to any LLM client to give your AI assistant reliable, deterministic TwinCAT code quality tooling — structural...

MCP tools for Novyx governed actions, shared memory, audit, rollback, and evidence workflows.

WaveSpeed MCP server — run any model on the live catalog (image, video, audio, 3D) with schema introspection, @path file upload, and price quotes

📚 MCP server for academic paper search and download.

Unlock the full potential of your reMarkable tablet as a for AI assistants. This MCP server lets Claude, VS Code Copilot, and other AI tools read, search, and traverse your entire reMarkable library...

v3.0.0 — The data plane now drives NotebookLM's (the same one the web app calls) instead of scraping the DOM — (list notebooks ~1 s vs ~30 s, generate a report ~13 s vs minutes), and more correct.
Agent Skills

你有没有遇到过这样的情况:换了老师之后,新老师讲的你怎么都听不懂?或者毕业了,再也没有人能像那个老师一样给你讲明白?

43 projects · 8 categories · End-to-end AI scientists · Experiment loops · Research co-pilots · Skill packs · Paper tools · Benchmarks

![Very Good Ventures][very_good_ventures_link_dark] ![Very Good Ventures][very_good_ventures_link_light]

它把角色卡、会话记忆、知识库、成员目录、技能系统、模型接入、Web Console,以及 OpenClaw 兼容 skill runtime 都收敛在同一个服务里;NapCat / OneBot 只负责 QQ 协议和消息收发。

上传你和 crush 的聊天记录,AI 模拟 ta 的性格,你在安全沙盒里反复练习——找到真诚又有效的沟通方式。 Upload your chat history with your crush. AI simulates their personality. Practice in a safe sandbox until you find your voice.

让你的 coding agent 的技能,从每一次真实会话里自我进化——你只管写代码。

- 与 是 skill 模式(被支持 Skills 的 IDE 加载执行),仅依赖可读的小程序源码目录 - 是独立的 Node 工程(含 CLI / Web UI),依赖 Node ≥ 18.17

is an open set of skills for the : proven instructions, workflows, and examples that help AI agents work with Spring Boot projects predictably.

A Claude Code skill for prompting Claude Fable 5 to orchestrate a build cheaply — Fable architects, Opus 4.8 executes.

Autofish gives any agent a stable, explicit, and observable Android execution layer: inspect the screen, act through stable refs instead of brittle coordinates, verify outcomes after every step, and...

微信读书前几天上了一个官方 AI skill(weread.qq.com/r/weread-skills),把书架、笔记、阅读统计、推荐 6 件事开放给 AI。能力很强,但它只是「自然语言包装的搜索接口」——你让它推荐书,它不会去看你已经读过什么,常把你笔记 68 条的书又当新书推回来给你。

For engineers who want agents shipping code without a human in the loop.