WorkflowySAFE
Powerful CLI and MCP server for WorkFlowy: reports, search/replace, backup support, and AI integration (Claude, LLMs)
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
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.
[](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
brew install mholzen/workflowy/workflowy-cli
Configure Your API Key
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
# 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.
U
3512e2576e0cOBSERVED · 2026-10-07Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add workflowy:0.9.0 --env WORKFLOWY_API_KEY=${WORKFLOWY_API_KEY} -- docker run -i --rm ghcr.io/mholzen/workflowy:0.9.0:NoneTrust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (5 observation(s))
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (4)
.goreleaser.yaml
#### Full Access (Read + Write)
# Full access
Gates applied: no_behavioural_pass.
3512e2576e0cfull audit observations/trust-audit/mcp-server/mholzen__workflowy-3.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-07 | 3512e2576e0c | SAFE | B | 89 | first audit |
Questions
What is the Workflowy MCP server?
Powerful CLI and MCP server for WorkFlowy: reports, search/replace, backup support, and AI integration (Claude, LLMs)
Is Workflowy safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Workflowy need?
It reads WORKFLOWY_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Workflowy run?
It speaks stdio, so it runs as a local process your client starts.
How current is this page?
The grade is for one exact copy of the source (3512e2576e0c), read on 2026-10-07. The repository is watched and re-audited when it changes.