
Workflowy
Connects Claude to Workflowy's API with full CRUD operations plus some genuinely useful power tools. You get the basics like creating, updating, and completing nodes, but the real draw is bulk regex search and replace with dry run mode, content transformations that can split nodes or pipe through shell commands, and usage reports that surface stale content or show where your outline is bloated. Supports offline mode via Dropbox backups and lets you sandbox AI writes to specific subtrees. Ships as both an MCP server and standalone CLI, so you can script the same operations outside of Claude. If you keep serious data in Workflowy and want programmatic access beyond their web UI, this gives you the full toolkit.
- GitHub stars
- 60
- tools
- 18
- auth
- Secret needed
- transport
- STDIO
- env var
- 1
- last updated
- Feb 10, 2026
Tools
18 toolsPublic tool metadata for what this MCP can expose to an agent.
workflowy_getGet a node and its descendants as a tree
Get a node and its descendants as a tree
No parameter schema in public metadata yet.
workflowy_listList descendants as a flat list
List descendants as a flat list
No parameter schema in public metadata yet.
workflowy_searchSearch nodes by text or regex
Search nodes by text or regex
No parameter schema in public metadata yet.
workflowy_targetsList shortcuts and system targets (inbox, etc.)
List shortcuts and system targets (inbox, etc.)
No parameter schema in public metadata yet.
workflowy_idResolve short ID or target key to full UUID
Resolve short ID or target key to full UUID
No parameter schema in public metadata yet.
workflowy_report_countFind where most of your content lives
Find where most of your content lives
No parameter schema in public metadata yet.
workflowy_report_childrenFind nodes with many children
Find nodes with many children
No parameter schema in public metadata yet.
workflowy_report_createdFind oldest nodes
Find oldest nodes
No parameter schema in public metadata yet.
workflowy_report_modifiedFind stale, unmodified nodes
Find stale, unmodified nodes
No parameter schema in public metadata yet.
workflowy_report_mirrorsFind most mirrored nodes (requires backup)
Find most mirrored nodes (requires backup)
No parameter schema in public metadata yet.
workflowy_createCreate new nodes
Create new nodes
No parameter schema in public metadata yet.
workflowy_updateUpdate node content
Update node content
No parameter schema in public metadata yet.
workflowy_moveMove node to a new parent
Move node to a new parent
No parameter schema in public metadata yet.
workflowy_deleteDelete nodes
Delete nodes
No parameter schema in public metadata yet.
workflowy_completeMark nodes complete
Mark nodes complete
No parameter schema in public metadata yet.
workflowy_uncompleteMark nodes incomplete
Mark nodes incomplete
No parameter schema in public metadata yet.
workflowy_replaceBulk find-and-replace with regex
Bulk find-and-replace with regex
No parameter schema in public metadata yet.
workflowy_transformTransform node content (split, trim, shell commands)
Transform node content (split, trim, shell commands)
No parameter schema in public metadata yet.
Sponsors
Configuration
WORKFLOWY_API_KEY*secretYour Workflowy API key (get it from https://workflowy.com/api-key/)
Readme
Workflowy MCP Server & CLI
A feature-rich Model Context Protocol (MCP) server and Command Line Interface (CLI) for Workflowy written in Go. Connect your AI assistant (Claude, ChatGPT, etc.) to your Workflowy data or run commands from a terminal emulator or script, including search, bulk replace, usage reports, and offline access capabilities.
Why This Workflowy MCP Server?
Details
- Repository
- github.com/mholzen/workflowy
- Category
- Search & Web Crawling
- Package
ghcr.io/mholzen/workflowy:0.8.1- Transport
- STDIO
- Auth
- Required
- Registry
- MCP registry, active