Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@AppFlowy MCP Server upload my meeting notes to AppFlowy with the title 'Weekly Team Sync'"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Claude Code 扩展工具，用于将生成的富文本内容自动上传至 AppFlowy
本项目是一个 Claude Code 扩展工具（MCP Server），用于将生成的富文本内容自动上传至 AppFlowy。它支持 macOS 和 Windows，推荐使用 uv 进行环境管理。
Related MCP server: Document Generator MCP
🚀 自动上传富文本内容到 AppFlowy
📝 支持 Markdown 语法解析（标题、列表、代码块、加粗、链接等）
🔒 安全的环境变量配置管理
🖥️ 跨平台支持（macOS、Linux、Windows）
安装 uv
macOS / Linux:
curl -LsSf https://astral.sh/uv/install.sh | shWindows (PowerShell):
irm https://astral.sh/uv/install.ps1 | iexPython 环境
Python 3.12 或更高版本
可以通过 python --version 检查版本
AppFlowy 账号
确保已注册 AppFlowy 账号
获取 Workspace ID 和 Parent View ID（见下方说明）
git clone https://github.com/18896101294/my-appflowy-mcp.git
cd my-appflowy-mcp使用 uv 自动安装项目依赖：
# uv 会自动创建虚拟环境并安装依赖
uv sync这将会：
自动创建 Python 虚拟环境（如果不存在）
安装 pyproject.toml 中定义的所有依赖：
mcp >= 1.25.0
requests >= 2.32.5
生成或更新 uv.lock 锁定文件
检查依赖是否安装成功：
# 查看已安装的包
uv pip list你应该能看到 mcp 和 requests 包已成功安装。
配置 Claude Code 时需要使用项目的绝对路径：
macOS / Linux:
# 在项目目录下执行
pwd
# 输出示例: /Users/yourname/my-appflowy-mcpWindows (PowerShell):
# 在项目目录下执行
$PWD.Path
# 输出示例: C:\Users\YourName\my-appflowy-mcp记下这个路径，稍后配置时需要使用。
Workspace ID：登录 AppFlowy 后，在设置中可以找到工作空间 ID
Parent View ID：打开目标文档父级页面，从 URL 或页面设置中获取
配置文件路径: ~/.claude/config.json
配置内容:
{
"mcpServers": {
"appflowy": {
"command": "uv",
"args": [
"run",
"/path/to/your/my-appflowy-mcp/appflowy_skill.py"
],
"env": {
"APPFLOWY_EMAIL": "your-email@example.com",
"APPFLOWY_PASSWORD": "your-password",
"APPFLOWY_WORKSPACE_ID": "your-workspace-id",
"APPFLOWY_PARENT_VIEW_ID": "your-parent-view-id"
}
}
}
}⚠️ 注意：
将
/path/to/your/my-appflowy-mcp/appflowy_skill.py替换为上一步获取的绝对路径 +/appflowy_skill.py例如：如果
pwd输出为/Users/john/my-appflowy-mcp，则完整路径为/Users/john/my-appflowy-mcp/appflowy_skill.py
配置文件路径:
通常位于: %APPDATA%\Claude\config.json
完整路径示例: C:\Users\YourUserName\AppData\Roaming\Claude\config.json
💡 提示: 您可以在文件资源管理器地址栏输入
%APPDATA%\Claude直接跳转。
配置内容 (注意路径转义):
⚠️ Windows 路径中的反斜杠
\在 JSON 中必须写成双反斜杠\\
{
"mcpServers": {
"appflowy": {
"command": "uv",
"args": [
"run",
"C:\\path\\to\\your\\my-appflowy-mcp\\appflowy_skill.py"
],
"env": {
"APPFLOWY_EMAIL": "your-email@example.com",
"APPFLOWY_PASSWORD": "your-password",
"APPFLOWY_WORKSPACE_ID": "your-workspace-id",
"APPFLOWY_PARENT_VIEW_ID": "your-parent-view-id"
}
}
}
}路径配置说明:
⚠️ 重要：
将
C:\\path\\to\\your\\my-appflowy-mcp\\appflowy_skill.py替换为实际路径必须使用双反斜杠
\\分隔符例如：如果
$PWD.Path输出为C:\Users\John\my-appflowy-mcp，则配置中应写为："C:\\Users\\John\\my-appflowy-mcp\\appflowy_skill.py"
Windows 特别说明:
uv 命令: 确保已安装 uv 并添加到 PATH 环境变量。如果不确定，可以将 "command": "uv" 改为 uv.exe 的完整路径。
配置保存后，需要完全重启 Claude Code：
# 退出当前 Claude Code 会话
exit
# 重新启动 Claude Code
claude code检查 MCP Server 状态：
/mcp list如果看到 appflowy 状态正常（绿色 ✓），表示配置成功！
向 Claude 发送指令，例如：
把这份代码说明写成文档上传到 AppFlowy，标题是《Windows配置说明》Claude 会自动调用 AppFlowy MCP Server 将内容上传到您配置的 AppFlowy 工作空间。
"将这段代码的使用说明整理成文档上传到 AppFlowy"
"把刚才的分析报告上传到 AppFlowy，标题是《性能分析报告》"
"创建一个 AppFlowy 文档，标题是《项目进度》，内容是今天完成的任务列表"
Python 版本不兼容:
# 检查 Python 版本
python --version
# 或
python3 --version确保版本 >= 3.12。如果版本过低，请升级 Python。
uv sync 失败:
# 清理缓存并重新安装
uv cache clean
uv sync --refresh虚拟环境问题:
# 删除虚拟环境并重新创建
rm -rf .venv # macOS/Linux
# 或
Remove-Item -Recurse -Force .venv # Windows PowerShell
# 重新同步
uv sync检查 uv 是否正确安装:
uv --version检查脚本路径是否正确:
确保 appflowy_skill.py 路径使用绝对路径
Windows 用户确保使用 \\ 转义
检查环境变量是否正确配置:
确认 APPFLOWY_EMAIL、APPFLOWY_PASSWORD 等都已填写
确认 Workspace ID 和 Parent View ID 正确
检查网络连接: 确保能够访问 AppFlowy 服务
验证凭据: 确认邮箱和密码正确
检查权限: 确认账号对目标工作空间有写入权限
MIT License
欢迎提交 Issue 和 Pull Request！
如有问题，请在 GitHub Issues 中提出。
将生成的文本内容上传到 AppFlowy 文档中。
会自动解析 Markdown 语法（标题、列表、代码块、加粗、链接等）。
Args:
title: 文档的标题
content: 文档的正文内容（支持 Markdown）
| Name | Required | Description | Default |
|---|---|---|---|
| title | Yes | ||
| content | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It states the tool uploads content and parses Markdown, but lacks details on permissions, error handling, rate limits, or what happens upon upload (e.g., creation vs. update). For a mutation tool with zero annotation coverage, this is insufficient behavioral disclosure.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is appropriately sized and front-loaded with the main purpose. The two sentences are efficient, and the Args section adds necessary parameter details without redundancy. It could be slightly more structured but avoids waste.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 2 parameters, no annotations, and an output schema (which reduces need to explain returns), the description is minimally adequate. It covers the basic action and parameters but lacks context on behavioral traits and usage scenarios. For a simple upload tool, it meets baseline but has clear gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate. It adds meaning by explaining that 'title' is the document title and 'content' is the body content supporting Markdown, which clarifies beyond the schema's basic types. However, it doesn't detail constraints like length or format, leaving some gaps.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: '将生成的文本内容上传到 AppFlowy 文档中' (upload generated text content to AppFlowy document). It specifies the verb (upload) and resource (AppFlowy document), though it doesn't differentiate from siblings since none exist. The mention of Markdown parsing adds specificity about content handling.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool versus alternatives is provided. The description mentions automatic Markdown parsing, which implies usage for formatted content, but lacks context about prerequisites, constraints, or typical scenarios. Without sibling tools, this is less critical, but still a gap in usage direction.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
With only one tool, there is no possibility of ambiguity or overlap with other tools. The tool's purpose is clearly defined as uploading document content to AppFlowy with Markdown parsing.
The single tool name 'upload_document_to_appflowy' follows a clear verb_noun pattern and is descriptive, so consistency is inherently perfect as there are no other tools to compare against.
A single tool is too few for a server named 'AppFlowy MCP Server', which suggests broader functionality for interacting with AppFlowy. This minimal set feels thin and incomplete for the apparent scope of document management or collaboration.
The tool surface is severely incomplete for an AppFlowy integration. It only allows uploading documents, with no tools for reading, updating, deleting, searching, or managing documents, creating significant gaps that will cause agent failures in typical workflows.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Share HTML/Markdown documents via URL instantly. Create, edit, delete docs from any AI tool.
MCP-native collaborative markdown editor with real-time AI document editing
Markdown workspace for AI agents: read, write, organize, and share markdown documents.
Clean, repair, and convert AI-generated Markdown to HTML/PDF/DOCX/PNG; save and share documents.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/18896101294/my-appflowy-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
