Workflowy Local Mcp

Name: Workflowy Local Mcp
Author: rodolfo-terriquez

@rodolfo-terriquez

About Workflowy Local Mcp

A desktop app that gives AI assistants full read/write access to your WorkFlowy account with fast local search. Caches your entire outline in local SQLite with full-text search - instant search across hundreds of thousands of nodes without hitting API rate limits.

#productivity #notes #outliner

Basic information

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "workflowy": {
      "command": "node",
      "args": [
        "/path/to/workflowy-local-mcp/dist-mcp/server.js"
      ],
      "env": {
        "WORKFLOWY_API_KEY": "your-api-key"
      }
    }
  }
}

Tools

List all saved bookmarks and the user's custom AI instructions. **Call this at the start of every conversation.**

Save a node ID with a friendly name and context notes for future sessions

Delete a saved bookmark by name

Read a node and its children via the LLM Doc API. Supports calendar targets (`today`, `tomorrow`, `next_week`, `inbox`) and configurable depth (1-10). Returns tag-as-key JSON format.

Edit nodes via the LLM Doc API. Supports `insert`, `update`, and `delete` operations in a single call. Can create nested structures with one request.

Search locally cached nodes by text. Returns results with breadcrumb paths and a preview of each result's children.

Full sync of all Workflowy nodes to local cache (rate limited to 1 request per minute)

Overview

What is Workflowy Local Mcp?

A desktop app that gives AI assistants full read/write access to your Workflowy account with local caching and instant search. It stores your entire outline in a local SQLite database with full-text search, avoiding Workflowy API rate limits. Your API key never leaves your machine.

How to use Workflowy Local Mcp?

Download the latest release, open the app, and enter your Workflowy API key (get one at workflowy.com/api-reference). Go to the Setup tab and copy the configuration snippet for your MCP client (Claude Desktop, Claude Code, Cursor, or any MCP app). Restart your client; the seven Workflowy tools become available: list_bookmarks, save_bookmark, delete_bookmark, read_doc, edit_doc, search_nodes, and sync_nodes.

Key features of Workflowy Local Mcp

7 tools for managing Workflowy nodes (read, edit, search, sync, bookmarks)
Local SQLite cache with fast full-text search across all nodes
Bookmarks to save frequently-used node locations with context notes
AI Instructions – create a node to customize LLM behavior across sessions
Sync-on-access – reads auto-sync so data is always fresh
Fully local – your API key never leaves your machine

Use cases of Workflowy Local Mcp

An AI assistant instantly searches hundreds of thousands of Workflowy nodes without rate limits
Add new tasks to a specific inbox or daily note using natural language
Edit multiple nodes in a single API call with batch insert/update/delete operations
Save bookmarks with context notes for quick navigation in future sessions
Set persistent AI preferences (e.g., “use checkboxes for tasks”) via an AI Instructions node

FAQ from Workflowy Local Mcp

How does it handle Workflowy’s API rate limits?

The app caches your outline locally. Searches use the SQLite cache (auto-synced when stale >1 hour), so you never hit the 1 request/minute rate limit on full exports. The LLM Doc API for reads and writes has no rate limit.

Where is my data stored?

All data is stored locally in the app data directory. On macOS: ~/Library/Application Support/com.workflowy.local-mcp/. On Windows: %APPDATA%\com.workflowy.local-mcp\. Files include config.json, bookmarks.db, and mcp-logs.json.