mcp-workflowy
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| WORKFLOWY_PASSWORD | Yes | Your Workflowy account password | |
| WORKFLOWY_USERNAME | Yes | Your Workflowy account username |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
| logging | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_nodesA | List nodes in Workflowy. If a |
| search_nodesB | Search nodes in Workflowy |
| create_nodeB | Create a new node |
| update_nodeB | Update an existing node |
| toggle_completeB | Toggle completion status of a node |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 5 tools
Each tool targets a distinct action—create, list, search, update, and toggle completion—so there is no major ambiguity. update_node and toggle_complete overlap somewhat in that both modify a node, but their purposes are clear enough. list_nodes and search_nodes are clearly differentiated by hierarchy vs. content search.
The tools mostly follow a consistent verb_noun pattern (create_node, list_nodes, update_node, search_nodes). toggle_complete breaks the pattern slightly by referencing a state rather than the node object, but all names remain simple and readable.
With exactly 5 tools, the server is well-scoped for managing Workflowy nodes. Each tool has a clear purpose and there is no bloat or minimalism that detracts from the domain.
The tool set covers create, list, search, update, and toggle completion, but lacks a delete_node or a dedicated get_node operation. These are notable gaps in the node lifecycle, though agents can partially work around them with search and list.