Skip to main content

Enhanced MCP server for Memos with complete CRUD and search capabilities

Project description

Memos MCP Server Enhanced

English | 中文

🇬🇧 English

An enhanced Model Context Protocol (MCP) server for Memos, enabling LLMs (like Claude, Cursor, etc.) to interact seamlessly with your Memos knowledge base.

Privacy Note: This project runs locally on your machine. Your Memos data is only accessed by the MCP client you authorize.

✨ Key Features

  • Complete CRUD: Create, read, update, and delete memos.
  • Smart Search: Support for natural language date filtering (e.g., "find notes from last week", "search for 'meeting' in 2024").
  • Task Management: Dedicated tools for managing TODO lists (list_todos, create_todo, complete_todo).
  • Resource Management: Upload files, manage attachments, and attach them to memos.
  • Batch Operations: Archive or delete multiple memos in one go.
  • Template System: Create memos from reusable templates with variable substitution.
  • Export Tools: Export content to Obsidian vaults or format for WeChat Official Accounts.

🚀 Quick Start

Prerequisites

  • A running Memos instance (v0.22+ recommended).
  • An API Token from Memos (Settings -> Access Tokens).
  • uv installed (recommended) or Python 3.10+.

Configuration (Claude Desktop / Cursor)

Add the following to your MCP configuration file:

{
  "memos": {
    "command": "uvx",
    "args": ["memos-mcp-enhanced"],
    "env": {
      "MEMOS_INSTANCE_URL": "https://your-memos-url.com",
      "MEMOS_API_TOKEN": "your-api-token-here"
    }
  }
}

📦 Installation (Local Development)

  1. Clone the repository:

    git clone https://github.com/yourusername/memos-mcp-enhanced.git
    cd memos-mcp-enhanced
    
  2. Create a .env file:

    cp .env.example .env
    # Edit .env with your configuration
    
  3. Run the server:

    uv run memos-mcp
    

🛠️ Available Tools

The server exposes 26 tools including:

  • search_memos: Search with keywords and date ranges.
  • create_memo / update_memo: Manage memo content and metadata (including backdating).
  • upload_resource / add_attachment: Handle files.
  • batch_operation: Bulk actions.
  • export_to_obsidian: Sync to your local vault.

🇨🇳 中文

Memos 的增强版 Model Context Protocol (MCP) 服务器。它赋予了 LLM(如 Claude, Cursor 等)读写和管理你 Memos 知识库的能力。

隐私说明:此服务在您的本地机器上运行。您的 Memos 数据仅在您授权的 MCP 客户端中处理,不会上传到任何第三方服务器。

✨ 核心功能

  • 全功能 CRUD: 创建、读取、更新、删除笔记。
  • 智能搜索: 支持自然语言的日期过滤搜索(支持如 "查找上周的笔记"、"搜索去年的记录" 等自然语言)。
  • 待办管理: 专门的 TODO 管理工具 (list_todos, create_todo, complete_todo)。
  • 附件管理: 支持文件上传、管理及绑定到笔记。
  • 批量操作: 支持批量归档、删除笔记。
  • 模板系统: 内置模板引擎,支持参数替换,快速生成周报、日记等。
  • 导出工具: 支持将笔记导出到 Obsidian 本地库,或格式化为微信公众号文章。

� 快速开始

前置要求

  • 一个运行中的 Memos 实例 (建议 v0.22+)。
  • Memos API Token (在 设置 -> Access Tokens 中获取)。
  • 安装 uv (推荐) 或 Python 3.10+。

配置方式 (Claude Desktop / Cursor)

在您的 MCP 配置文件中添加以下内容:

{
  "memos": {
    "command": "uvx",
    "args": ["memos-mcp-enhanced"],
    "env": {
      "MEMOS_INSTANCE_URL": "https://your-memos-url.com",
      "MEMOS_API_TOKEN": "your-api-token-here"
    }
  }
}

📦 本地开发安装

  1. 克隆仓库:

    git clone https://github.com/yourusername/memos-mcp-enhanced.git
    cd memos-mcp-enhanced
    
  2. 配置环境变量:

    cp .env.example .env
    # 编辑 .env 文件填入你的 API 信息
    
  3. 运行服务:

    uv run memos-mcp
    

🛠️ 可用工具

本服务提供 26 个增强工具,包括但不限于:

  • search_memos: 支持关键词和自然语言日期范围搜索。
  • create_memo / update_memo: 管理笔记内容、属性(支持修改显示时间)。
  • upload_resource / add_attachment: 文件上传与附件管理。
  • batch_operation: 批量处理。
  • export_to_obsidian: 导出到本地 Obsidian 库。

License

MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

memos_mcp_enhanced-0.1.0.tar.gz (29.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

memos_mcp_enhanced-0.1.0-py3-none-any.whl (30.7 kB view details)

Uploaded Python 3

File details

Details for the file memos_mcp_enhanced-0.1.0.tar.gz.

File metadata

  • Download URL: memos_mcp_enhanced-0.1.0.tar.gz
  • Upload date:
  • Size: 29.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.9.25 {"installer":{"name":"uv","version":"0.9.25","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":null,"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for memos_mcp_enhanced-0.1.0.tar.gz
Algorithm Hash digest
SHA256 abca34234cb4c0739a7456159e38a9418267aba12f92a75f975ad2d06a3819f4
MD5 111910777b70101de22ab92d8c1773dd
BLAKE2b-256 ab00da199339c0692d599a033f82fdcb0f5866c19c6903652ceb393f03fdc7c9

See more details on using hashes here.

File details

Details for the file memos_mcp_enhanced-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: memos_mcp_enhanced-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 30.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.9.25 {"installer":{"name":"uv","version":"0.9.25","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":null,"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for memos_mcp_enhanced-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 bb66e99a9093729d86176e443f02f4f5ea04541e656d5ef6c2f8c81fdf5e44b8
MD5 a2818bf49b90ef1b76b553f722e2fabc
BLAKE2b-256 1c89f1d5bc7e708cd34ecb0b1fbf05ce5603cc1777d7596e7c416809478be9c3

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page