Skip to main content
Glama
jiangxtx

yinxiang-mcp

by jiangxtx

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

Related MCP server: Evernote MCP Server

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

  • URLhttp://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.

Related MCP Connectors

Related MCP Servers

  • F
    license
    Not graded
    quality
    D
    maintenance
    A Model Context Protocol server that allows AI assistants like Claude to interact with Evernote, enabling them to create, search, read, and manage notes through natural language.
    4
    -
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables Claude to interact with Evernote notes and notebooks, supporting full-text search, note operations (create, read, update, delete), and multiple output formats for both International Evernote and Yinxiang Biji.
    11
    MIT