get_note_labels
AI agents call get_note_labels to retrieve information from NotesKeep MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves label metadata associated with a note—a read-only query operation with no side effects. No data is created, modified, or deleted. The empty description reduces confidence slightly, but the naming convention and sibling tool context strongly indicate a safe read operation. Severity is low because exposing note label information has minimal blast radius.
From the tool's definition Tool name 'get_note_labels' indicates a retrieval operation. Sibling tools clarify context: 'add_label_to_note', 'create_label', 'delete_label' are write/destructive operations, while 'get_note', 'list_labels', 'list_notes' are clearly read operations.
Attacks that exploit this kind of access
get_note_labels. It is categorised as a Read tool in the NotesKeep MCP Server MCP Server, which means it retrieves data without modifying state.
Register the NotesKeep MCP Server MCP server in PolicyLayer and add a rule for get_note_labels: 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 NotesKeep MCP Server. Nothing to install.
get_note_labels is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_note_labels 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 get_note_labels. 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.
get_note_labels is provided by the NotesKeep MCP Server MCP server (mariomosca/noteskeep-mcp). 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 →