Rename an existing category inside Notes.
AI agents use edit_category to create or update resources in Nextcloud Notes — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Nextcloud Notes environment.
This tool modifies data but is not irreversible (can be renamed back), does not delete data, and does not execute arbitrary code or move money. It falls clearly into Write. Severity is medium because renaming a category in a notes application could affect organization and access patterns, but the blast radius is limited to note categorization metadata.
From the tool's definition The tool 'edit_category' performs 'Rename an existing category inside Notes' — this modifies existing data (the category name) reversibly. It is a write operation that can be undone by renaming again.
Attacks that exploit this kind of access
Rename an existing category inside Notes. It is categorised as a Write tool in the Nextcloud Notes MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Nextcloud Notes MCP server in PolicyLayer and add a rule for edit_category: 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 Nextcloud Notes. Nothing to install.
edit_category 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_category 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_category. 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_category is provided by the Nextcloud Notes MCP server (rncz/nextcloud-notes-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 →