io.github.bahfahh/noteit-mcp
编码与调试by bahfahh
面向 AI agent 档案与智能笔记的 MCP server,内置 60+ 编程 prompt 包和专家 persona 模板。
什么是 io.github.bahfahh/noteit-mcp?
面向 AI agent 档案与智能笔记的 MCP server,内置 60+ 编程 prompt 包和专家 persona 模板。
README
Noteit MCP
🩹 The cure for AI "Markdown Hell" - AI prompt library + visual knowledge hub for developers
Noteit-MCP transforms drowning in 5,000-word documents into navigable HTML and logic diagrams instantly. With 60+ expert personas, organize complex ideas without cognitive overload. Makes Specification-Driven Development actually human-readable.
✨ Demo & Screenshots
🎥 Noteit MCP in Action - Complete usage walkthrough
<p align="center"> <a href="https://www.youtube.com/watch?v=-cRqrBOzKIc&t=24s"> <img src="https://img.youtube.com/vi/-cRqrBOzKIc/0.jpg" alt="Noteit MCP Demo Video" width="800" /> </a> <br /> <em>🎬 Click to watch the complete demo</em> </p> <p align="center"> <img src="assets/demo/noteweb.png" alt="Noteit Dashboard" width="800" /> <br /> <em>📊 Unified dashboard with agent profiles and note management</em> </p> <p align="center"> <img src="assets/demo/noteweb2.png" alt="Agent Profiles" width="800" /> <br /> <em>🤖 40+ pre-built agent templates for different coding tasks</em> </p> <p align="center"> <img src="assets/demo/noteweb3.png" alt="Note Taking" width="800" /> <br /> <em>📝 AI-readable notes with graph visualizations</em> </p>1) What is Noteit MCP?
Noteit MCP is an HTTP MCP server (Next.js API route) that lets AI coding tools securely access two core systems:
- Agent Profiles: Composable configurations (personas, instructions, rules, documents) that shape AI behavior for specific tasks.
- Notes: Personal note-taking with structured records and graph visualizations.
Authentication uses OAuth 2.1 with device fingerprint for IDEs that support it, with an optional API Token flow for other MCP clients. The server endpoint is exposed at /api/mcp.
2) Why use Noteit MCP?
- Unified configuration: Reusable agent profiles that any AI client can adopt.
- Productive note-taking: AI-readable notes, tasks, and visual graphs.
- Secure by design: OAuth 2.1 + transparent token refresh; API token for non‑OAuth clients.
- Works across IDEs: Cursor, Claude Code, Gemini CLI, Claude Desktop (via proxy), and more.
3) How to connect
The MCP server is at https://www.noteit-mcp.com/api/mcp.
Cursor (mcp.json)
Create or update ~/.cursor/mcp.json:
{
"mcpServers": {
"noteit-mcp": {
"url": "https://www.noteit-mcp.com/api/mcp"
}
}
}
Then restart Cursor. OAuth will be handled automatically.
Claude Code (built-in MCP)
Use the command-line helper (global scope):
claude mcp add --transport http noteit-mcp https://www.noteit-mcp.com/api/mcp
Or project scope:
claude mcp add -s project --transport http noteit-mcp https://www.noteit-mcp.com/api/mcp
Gemini CLI
Add the server and authenticate:
gemini mcp add --transport http noteit-mcp https://www.noteit-mcp.com/api/mcp
/mcp auth noteit-mcp
/mcp # verify tools are listed
Other IDEs (API Token)
Login at https://www.noteit-mcp.com to obtain an API token.
4) Available Tools
Through Noteit-MCP, agents can use the following tools:
- noteit_profiles_list: List user agent profiles - configuration sets containing personas, instructions, rules, and documents for specific roles or tasks
- noteit_profiles_getConfig: Retrieve a composable AI agent configuration profile containing personas, instructions, rules, and documents
- noteit_profiles_generate: Generate and save individual configuration components (persona, rule, document, instruction) that can be assembled into agent profiles
- noteit_notes_create: Create project notes with 4 specialized types: "note" for general records, "task" for development assignments, "why" for explanations, "issue" for problems and bugs
- noteit_notes_read: Retrieve complete content of a specific note by its unique ID
- noteit_notes_list: Browse and filter all user notes across projects with optional filtering by tags, record types, or project names
- noteit_web_create: Generate interactive HTML notes to help developers understand complex concepts, processes, or technical details
- noteit_flow_create: Create visual flow diagrams with nested data support for technical process visualization
⭐ Star this project
If Noteit MCP helps streamline your AI workflow, please give it a star! It helps others discover this tool and motivates continued development.
License
MIT
常见问题
io.github.bahfahh/noteit-mcp 是什么?
面向 AI agent 档案与智能笔记的 MCP server,内置 60+ 编程 prompt 包和专家 persona 模板。
相关 Skills
前端设计
by anthropics
面向组件、页面、海报和 Web 应用开发,按鲜明视觉方向生成可直接落地的前端代码与高质感 UI,适合做 landing page、Dashboard 或美化现有界面,避开千篇一律的 AI 审美。
✎ 想把页面做得既能上线又有设计感,就用前端设计:组件到整站都能产出,难得的是能避开千篇一律的 AI 味。
网页应用测试
by anthropics
用 Playwright 为本地 Web 应用编写自动化测试,支持启动开发服务器、校验前端交互、排查 UI 异常、抓取截图与浏览器日志,适合调试动态页面和回归验证。
✎ 借助 Playwright 一站式验证本地 Web 应用前端功能,调 UI 时还能同步查看日志和截图,定位问题更快。
网页构建器
by anthropics
面向复杂 claude.ai HTML artifact 开发,快速初始化 React + Tailwind CSS + shadcn/ui 项目并打包为单文件 HTML,适合需要状态管理、路由或多组件交互的页面。
✎ 在 claude.ai 里做复杂网页 Artifact 很省心,多组件、状态和路由都能顺手搭起来,React、Tailwind 与 shadcn/ui 组合效率高、成品也更精致。
相关 MCP Server
GitHub
编辑精选by GitHub
GitHub 是 MCP 官方参考服务器,让 Claude 直接读写你的代码仓库和 Issues。
✎ 这个参考服务器解决了开发者想让 AI 安全访问 GitHub 数据的问题,适合需要自动化代码审查或 Issue 管理的团队。但注意它只是参考实现,生产环境得自己加固安全。
Context7 文档查询
编辑精选by Context7
Context7 是实时拉取最新文档和代码示例的智能助手,让你告别过时资料。
✎ 它能解决开发者查找文档时信息滞后的问题,特别适合快速上手新库或跟进更新。不过,依赖外部源可能导致偶尔的数据延迟,建议结合官方文档使用。
by tldraw
tldraw 是让 AI 助手直接在无限画布上绘图和协作的 MCP 服务器。
✎ 这解决了 AI 只能输出文本、无法视觉化协作的痛点——想象让 Claude 帮你画流程图或白板讨论。最适合需要快速原型设计或头脑风暴的开发者。不过,目前它只是个基础连接器,你得自己搭建画布应用才能发挥全部潜力。