Workflowy MCP Server
Enables LLMs to interact with Workflowy through the Model Context Protocol, supporting operations like creating, updating, deleting, and listing nodes.
README
Workflowy MCP Server
Workflowy MCP Server for Nanobot - 讓 nanobot 可以透過 Model Context Protocol 操作 Workflowy。
功能
list_targets- 列出所有可用的 targets (inbox, home 等)list_nodes- 列出指定 parent 的子節點get_node- 取得單一節點的詳細資訊create_node- 建立新節點update_node- 更新節點內容delete_node- 刪除節點move_node- 移動節點到新的父節點complete_node- 標記節點為完成uncomplete_node- 取消節點的完成狀態export_all_nodes- 匯出所有節點
安裝
# 使用 uvx 直接執行
uvx workflowy-mcp
# 或先安裝後使用
pip install workflowy-mcp
workflowy-mcp
# nanobot 使用特定的虛擬環境,先啟動該 venv,然後執行: (推薦)
source /path/to/nanobot-venv/bin/activate
pip install /home/user/workspace/workflowy-mcp
設定
1. 取得 Workflowy API Key
前往 https://workflowy.com/api-key 取得 API Key。
2. 設定 nanobot config
在 nanobot 的設定檔中加入:
{
"tools": {
"mcpServers": {
"workflowy": {
"command": "uvx",
"args": ["workflowy-mcp"],
"env": {
"WORKFLOWY_API_KEY": "your-api-key",
"WORKFLOWY_DEFAULT_PARENT": "home"
}
}
}
}
}
環境變數
| 變數 | 說明 | 必填 | 預設 |
|---|---|---|---|
WORKFLOWY_API_KEY |
Workflowy API Key | 是 | - |
WORKFLOWY_DEFAULT_PARENT |
預設 parent_id | 否 | inbox |
使用方式
nanobot 啟動後,LLM 可以使用以下 tools:
mcp_workflowy_list_targets - 列出所有 targets
mcp_workflowy_list_nodes - 列出子節點 (parent_id 預設為 inbox)
mcp_workflowy_get_node - 取得節點詳情
mcp_workflowy_create_node - 建立新節點
mcp_workflowy_update_node - 更新節點
mcp_workflowy_delete_node - 刪除節點
mcp_workflowy_move_node - 移動節點
mcp_workflowy_complete_node - 標記完成
mcp_workflowy_uncomplete_node - 取消完成
mcp_workflowy_export_all_nodes - 匯出所有節點
範例
# 在 inbox 建立新任務
mcp_workflowy_create_node(
parent_id="inbox",
name="每週回顧",
note="每週五下午進行",
layout_mode="todo"
)
# 列出 inbox 的內容
mcp_workflowy_list_nodes(parent_id="inbox")
# 移動節點到 home
mcp_workflowy_move_node(
id="xxx-xxx-xxx",
parent_id="home",
position="top"
)
parent_id 可用值
"inbox"- 預設的收件匣"home"- 預設的首頁"None"- 頂層節點- UUID - 任意節點的 ID
開發
# 安裝開發依賴
pip install -e ".[dev]"
# 執行
python -m workflowy_mcp
# 測試
pytest
License
MIT
Recommended Servers
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.
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.
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.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
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.
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.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.