yinxiang-mcp

yinxiang-mcp

MCP server for Evernote China (印象笔记), enabling Claude to list notebooks and notes, search, read, create, and update notes via natural language.

Category
Visit Server

README

印象笔记 MCP Server

基于印象笔记 Developer API 构建的 MCP (Model Context Protocol) Server,让 Claude 能够直接操作你的印象笔记账户。

功能

Tool 功能
yinxiang_list_notebooks 列出所有笔记本(含 GUID)
yinxiang_list_notes 列出笔记,支持按笔记本过滤和分页
yinxiang_search_notes 全文检索笔记(支持印象笔记搜索语法)
yinxiang_get_note 获取指定笔记的完整内容
yinxiang_create_note 创建新笔记(Markdown → ENML 自动转换)
yinxiang_update_note 更新笔记标题或内容

快速开始

第一步:获取 Developer Token

  1. 访问 https://app.yinxiang.com/api/DeveloperToken.action
  2. 点击 "Create a developer token"
  3. 复制以 S=s1: 开头的 Token,填入 .env 文件

第二步:安装依赖

cd ~/mcp-servers/yinxiang-mcp
uv venv --python 3.11
uv pip install -r requirements.txt

第三步:启动 HTTP Server

./start.sh       # 后台启动(端口 8765)
./status.sh      # 查看状态
./stop.sh        # 停止服务

第四步(可选):开机自启

cp com.yinxiang.mcp.plist ~/Library/LaunchAgents/
launchctl load ~/Library/LaunchAgents/com.yinxiang.mcp.plist

接入 MCP 客户端

Server 启动后,所有支持 MCP 的客户端均可通过以下端点接入:

http://127.0.0.1:8765/mcp

Claude Code

~/.claude/settings.json 中添加:

"yinxiang": {
  "url": "http://127.0.0.1:8765/mcp"
}

CatPaw / 其他 MCP 客户端

在客户端的 MCP 配置中填入:

  • 类型:Streamable HTTP
  • URL:http://127.0.0.1:8765/mcp

搜索语法说明

印象笔记支持丰富的搜索语法:

语法 示例 说明
关键词 Python 学习 全文搜索
notebook: notebook:工作 按笔记本名称
tag: tag:重要 按标签
intitle: intitle:会议记录 按标题关键词
created: created:20240601 按创建日期
updated: updated:20240101 按更新日期
组合使用 tag:工作 intitle:周报 多条件组合

注意事项

  • Token 安全:Developer Token 有完整账户访问权限,请妥善保管,不要提交到代码仓库
  • API 频率限制:印象笔记限制每小时每用户的 API 调用次数,个人正常使用不会触发
  • ENML 格式:笔记内容使用 ENML(印象笔记 XML 格式),工具会自动完成 Markdown ↔ ENML 转换
  • 中国版专用:本服务器配置为印象笔记中国版(app.yinxiang.com),不兼容国际版 Evernote

For AI Agents / 自动化安装指南

If a user asks you to install this MCP server, please follow these EXACT steps strictly:

  1. Clone & Setup Environment: Clone the repository to a suitable location. Create a Python 3.11+ virtual environment (python -m venv .venv or uv venv) and install dependencies from requirements.txt.

  2. Ask for Developer Token (CRITICAL): You CANNOT generate the Evernote/Yinxiang developer token for the user. You MUST pause and ask the user to provide it. Provide them this exact link: https://app.yinxiang.com/api/DeveloperToken.action Wait for their reply with the token (starting with S=s...).

  3. Configure MCP Client (Use stdio mode): Once you have the token, DO NOT use the HTTP mode or start.sh. Configure the user's IDE/MCP Client using the stdio transport. Set the configuration as follows:

    • Command: /path/to/repo/.venv/bin/python (use the absolute path to the venv python)
    • Arguments: ["/path/to/repo/server.py"] (absolute path)
    • Environment Variables: {"YINXIANG_TOKEN": "the_token_user_provided"}
  4. Verify: Inform the user that the installation is complete and the MCP is registered via stdio.

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured