
Micro.blog Books MCP Server
Enables management of Micro.blog book collections through natural language, allowing users to organize bookshelves, add/move books, and track reading goals. Built with FastMCP for reliable integration with Claude Desktop.
README
Micro.blog Books MCP Server
An MCP (Model Context Protocol) server built with FastMCP that provides access to the Micro.blog Books API, allowing Claude Desktop (or other MCP clients) to manage your book collections, bookshelves, and reading goals.
Overview
This server enables Claude Desktop to interact directly with your Micro.blog book collection through a clean set of tools that cover all aspects of book management - from organizing bookshelves to tracking reading goals. Built with FastMCP for simplicity and reliability.
Features
This MCP server provides the following tools for managing your Micro.blog books:
Bookshelf Management
- get_bookshelves: Get all your bookshelves
- get_bookshelf_books: Get books in a specific bookshelf
- add_bookshelf: Create a new bookshelf
- rename_bookshelf: Rename an existing bookshelf
Book Management
- add_book: Add a new book to a bookshelf
- move_book: Move a book between bookshelves
- remove_book: Remove a book from a bookshelf
- change_book_cover: Update a book's cover image
Reading Goals
- get_reading_goals: Get your reading goals
- get_goal_progress: Get progress toward a specific reading goal
- update_reading_goal: Update a reading goal's target or progress
Prerequisites
- Python 3.8 or higher (FastMCP has lower requirements)
- Micro.blog account with API access
- Claude Desktop application
Installation
Quick Setup (Recommended)
-
Clone this repository:
git clone https://github.com/7robots/micro-mcp-server.git cd micro-mcp-server
-
Run the automated setup:
python install.py
This installs FastMCP and all dependencies, then verifies everything works.
Manual Setup
If you prefer manual installation:
-
Install dependencies:
pip install -r requirements.txt
This installs FastMCP and all required packages.
-
Verify installation:
python run_server.py --help
Setup
1. Get Your Micro.blog Bearer Token
You'll need a bearer token from Micro.blog to authenticate API requests. You can get this from your Micro.blog account settings.
2. Configure Environment
Set your bearer token as an environment variable:
export MICRO_BLOG_BEARER_TOKEN="your_token_here"
3. Configure Claude Desktop
Option A: Automatic Configuration (Recommended)
Run the configuration generator:
python get_config.py
This will output the exact configuration you need and save it to claude_desktop_config.json
.
Option B: Manual Configuration
Add the MCP server to your Claude Desktop configuration. The configuration file is typically located at:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json
- Windows:
%APPDATA%\Claude\claude_desktop_config.json
Add the following to your configuration:
{
"mcpServers": {
"micro-books": {
"command": "/opt/anaconda3/bin/python3",
"args": [
"/path/to/micro-mcp-server/run_server.py"
],
"env": {
"MICRO_BLOG_BEARER_TOKEN": "your_token_here"
}
}
}
}
Important Notes:
- The configuration generator automatically finds a compatible Python version
- Replace
your_token_here
with your actual Micro.blog bearer token - Use full absolute paths for both the Python executable and script
4. Restart Claude Desktop
After updating the configuration, restart Claude Desktop for the changes to take effect.
Usage
Once configured, you can ask Claude to help manage your books. For example:
- "Show me all my bookshelves"
- "Add a new book called 'Project Hail Mary' by Andy Weir to my 'Currently reading' bookshelf"
- "Move book ID 79 to bookshelf ID 23"
- "What are my reading goals for this year?"
- "Update my reading goal to 25 books"
Contributing
Contributions are welcome! Please feel free to submit a Pull Request. For major changes, please open an issue first to discuss what you would like to change.
License
This project is licensed under the MIT License - see the LICENSE file for details.
API Reference
All tools return JSON responses from the Micro.blog API. The server handles authentication automatically using your bearer token.
For more details about the underlying API, see the Micro.blog Books API documentation.
Troubleshooting
- Authentication errors: Make sure your
MICRO_BLOG_BEARER_TOKEN
is set correctly and valid - Server not appearing in Claude: Check that the path in your configuration is correct and that uv is installed
- Permission errors: Ensure the server files have appropriate permissions
Development
To run the server in development mode:
cd micro-mcp-server
python run_server.py --bearer-token "your_token_here"
Troubleshooting
Common Issues
-
spawn python ENOENT
error: This means Claude Desktop can't find the Python executable. Use the configuration generator (python get_config.py
) to get the correct paths. -
Import errors: Make sure you've run the setup script (
python install.py
) to install FastMCP and dependencies. -
Authentication errors: Verify your
MICRO_BLOG_BEARER_TOKEN
is set correctly and valid in the Claude Desktop configuration. -
Path errors: Ensure both the Python executable and
run_server.py
paths are full absolute paths in your configuration.
Testing the Server
You can test the server independently:
# Test with your actual token
python run_server.py --bearer-token "your_actual_token"
# Or test the installation
python install.py
推荐服务器

Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。