AI agents use edit_folder to create or update resources in Joplin — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Joplin environment.
The tool modifies folder/notebook properties (e.g., name, metadata) reversibly. This is a Write operation—data is changed but can be undone by editing again. It does not delete data (Destructive), execute arbitrary code (Execute), or move money (Financial). Severity is medium because uncontrolled folder edits could disrupt note organization, but the effect is recoverable.
From the tool's definition Tool name 'edit_folder' and description 'Edit/update an existing folder/notebook in Joplin' indicate modification of existing data structures without deletion or irreversible destruction.
Attacks that exploit this kind of access
Edit/update an existing folder/notebook in Joplin. It is categorised as a Write tool in the Joplin MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Joplin MCP server in PolicyLayer and add a rule for edit_folder: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Joplin. Nothing to install.
edit_folder is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the edit_folder rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for edit_folder. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
edit_folder is provided by the Joplin MCP server (joplin-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →