# Workflowy > Powerful CLI and MCP server for WorkFlowy: reports, search/replace, backup support, and AI integration (Claude, LLMs) - **Type:** MCP server - **Install:** `agentstack add mcp-mholzen-workflowy` - **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior - **Seller:** [mholzen](https://agentstack.voostack.com/s/mholzen) - **Installs:** 0 - **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml) - **Latest version:** 0.1.0 - **License:** MIT - **Upstream author:** [mholzen](https://github.com/mholzen) - **Source:** https://github.com/mholzen/workflowy - **Website:** https://workflowy.com ## Install ```sh agentstack add mcp-mholzen-workflowy ``` Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent. ## About # Workflowy MCP Server & CLI A feature-rich **Model Context Protocol (MCP) server** and **Command Line Interface (CLI)** for [Workflowy](https://workflowy.com) 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. [](https://go.dev/) [](https://github.com/mholzen/workflowy) [](https://modelcontextprotocol.io) [](LICENSE) ## Why This Workflowy MCP Server? - Full-text search with regex - Bulk search & replace - Content transformation (split, clean, pipe to LLMs) - Usage reports (stale nodes, size analysis, mirrors) - Sandboxed AI access with `--write-root-id` - Offline mode via backup files - CLI + MCP server in one tool - Caching for performance - Homebrew installation - Basic CRUD operations - Using short IDs (Copy Internal Link) ## Quick Start ### Install via Homebrew ```bash brew install mholzen/workflowy/workflowy-cli ``` ### Configure Your API Key ```bash mkdir -p ~/.workflowy echo "your-api-key-here" > ~/.workflowy/api.key ``` Get your API key at https://workflowy.com/api-key/ ### Run Your First Command ```bash # Get the top-level nodes, and nodes two levels deep workflowy get # Generate a report showing where most of your nodes are workflowy report count | pbcopy # paste directly into Workflowy! ``` Use `pbcopy` on macOS, `clip` on Windows, `wl-copy` on Linux, or `xclip` for X11 systems. ## Use with Claude Desktop or Claude Code ### Claude Code ```bash claude mcp add --transport=stdio workflowy -- workflowy mcp --expose=all ``` Remove `—expose=all` to limit to read-only tools. ### Claude Desktop Add to your configuration file: - **macOS**: `~/Library/Application Support/Claude/claude_desktop_config.json` - **Windows**: `%APPDATA%\Claude\claude_desktop_config.json` ```json { "mcpServers": { "workflowy": { "command": "workflowy", "args": ["mcp", "--expose=all"] } } } ``` Restart Claude Desktop and start asking Claude to work with your Workflowy! ## MCP Tools for AI Assistants ### Read Tools (Safe) | Tool | Description | |------|-------------| | `workflowy_get` | Get a node and its descendants as a tree | | `workflowy_list` | List descendants as a flat list | | `workflowy_search` | Search nodes by text or regex | | `workflowy_targets` | List shortcuts and system targets (inbox, etc.) | | `workflowy_id` | Resolve short ID or target key to full UUID | | `workflowy_report_count` | Find where most of your content lives | | `workflowy_report_children` | Find nodes with many children | | `workflowy_report_created` | Find oldest nodes | | `workflowy_report_modified` | Find stale, unmodified nodes | | `workflowy_report_mirrors` | Find most mirrored nodes (requires backup) | ### Write Tools | Tool | Description | |------|-------------| | `workflowy_create` | Create new nodes | | `workflowy_update` | Update node content | | `workflowy_move` | Move node to a new parent | | `workflowy_delete` | Delete nodes | | `workflowy_complete` | Mark nodes complete | | `workflowy_uncomplete` | Mark nodes incomplete | | `workflowy_replace` | Bulk find-and-replace with regex | | `workflowy_transform` | Transform node content (split, trim, shell commands) | ## CLI Features ### Search Your Entire Outline ```bash # Find all TODOs (case-insensitive) workflowy search -i "foobar" # Regex search for dates workflowy search -E "" # Search within a specific subtree (using Internal Link) workflowy search "bug" --item-id https://workflowy.com/#/1bdae4aecf00 ``` ### Bulk Search and Replace ```bash # Preview changes first (dry run) workflowy replace --dry-run "foo" "bar" # Interactive confirmation workflowy replace --interactive "foo" "bar" # Use regex capture groups workflowy replace "TASK-([0-9]+)" 'ISSUE-$1' ``` ### Some Common CRUD Operations ```bash # Add a task to your inbox workflowy create "Buy groceries" --parent-id=inbox # Change the name of an item workflowy update xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx --name "Project Plan v2" # Move an item to a different parent workflowy move # Mark a node as complete, using a short ID workflowy complete https://workflowy.com/#/xxxxxxxxxxxx # Resolve a short ID or target key to full UUID workflowy id inbox ``` ### Transform Content ```bash # Split a node's content by newlines into child nodes workflowy transform split -s "\n" # Clean up text workflowy transform trim workflowy transform no-punctuation # Pipe content through any shell command (e.g., an LLM) workflowy transform -x 'echo {} | llm "summarize this"' ``` ### Usage Reports ```bash # Where is most of my content? workflowy report count --threshold 0.01 # Which nodes have the most children? workflowy report children --top-n 20 # Find stale content (oldest modified) workflowy report modified --top-n 50 # Find most mirrored nodes (requires backup) workflowy report mirrors --top-n 20 ``` ## Data Access Methods Choose the best method for your use case: | Method | Speed | Freshness | Offline | Best For | |--------|-------|-----------|---------|----------| | `--method=get` | Medium | Real-time | No | Specific items | | `--method=export` | Fast* | 1 min worst case (due to rate limiting) | No | Full tree access | | `--method=backup` | Fastest | Stale | **Yes** | Bulk operations | *Cached after first fetch ### Offline Mode with Dropbox Backup Enable Workflowy's Dropbox backup and access your data offline: ```bash workflowy get --method=backup workflowy search -i "project" --method=backup ``` ## Installation Options ### Homebrew (macOS & Linux) ```bash brew install mholzen/workflowy/workflowy-cli ``` ### Scoop (Windows) ```powershell scoop bucket add workflowy https://github.com/mholzen/scoop-workflowy scoop install workflowy ``` ### Go Install ```bash go install github.com/mholzen/workflowy/cmd/workflowy@latest ``` ### Download Binary Download pre-built binaries from [GitHub Releases](https://github.com/mholzen/workflowy/releases/latest). ### Docker ```bash docker run --rm -e WORKFLOWY_API_KEY=your-key ghcr.io/mholzen/workflowy:latest get ``` ### From Source ```bash git clone https://github.com/mholzen/workflowy.git cd workflowy go build ./cmd/workflowy ``` ## Documentation - [Full CLI Reference](docs/CLI.md) - [MCP Server Guide](docs/MCP.md) - [API Reference](https://workflowy.com/api-reference/) - [Changelog](CHANGELOG.md) ## Examples ### AI Assistant Workflows Ask Claude: - "Search my Workflowy for all items containing 'meeting notes'" - "Show me nodes I haven't touched in 6 months" - "Replace all 'v1' with 'v2' in my Project A folder" - "What's taking up the most space in my outline?" - "Which nodes are mirrored the most?" - "Move this item to my inbox" ### CLI Workflows ```bash # Morning review: find stale items workflowy report modified --top-n 20 # Weekly cleanup: find oversized nodes workflowy report count --threshold 0.05 # Find unnecessary mirrors workflowy report mirrors --top-n 20 # Bulk rename: update project prefix workflowy replace "OLD-" "NEW-" --parent-id projects-folder-id # Split pasted content into child nodes workflowy transform split -s "\n" ``` ## Contributing Contributions welcome! See the [Contributing Guide](CONTRIBUTING.md). ```bash # Development setup git clone https://github.com/mholzen/workflowy.git cd workflowy go test ./... ``` ## License MIT — see [LICENSE](LICENSE) ## Acknowledgments - Thanks to Andrew Lisy for requesting a method to sandbox write commands - Thanks to Craig P. Motlin for pointing out mirrors are defined in the backup files ## Source & license This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code. - **Author:** [mholzen](https://github.com/mholzen) - **Source:** [mholzen/workflowy](https://github.com/mholzen/workflowy) - **License:** MIT - **Homepage:** https://workflowy.com Install and usage instructions live in the source repository linked above. ## Pricing - **Free** — Free ## Security capabilities Automated source analysis of v0.1.0 — what this tool can access: - **Network access:** no - **Filesystem access:** no - **Shell / process execution:** no - **Environment & secrets:** no - **Dynamic code execution:** no *"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.* ## Versions - **0.1.0** — security scan: passed — Imported from the upstream source. ## Links - Listing page: https://agentstack.voostack.com/l/mcp-mholzen-workflowy - Seller: https://agentstack.voostack.com/s/mholzen - Browse the marketplace: https://agentstack.voostack.com/browse --- Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.