AI agents use add_label_to_task to create or update resources in Nubis — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Nubis environment.
This tool adds a label to an existing task, which is a reversible modification of task data. It does not execute code, delete data, or involve financial operations. The blast radius is minimal since labeling is a low-impact organizational operation that can be easily undone or corrected.
From the tool's definition Tool name 'add_label_to_task' and description 'Add a label to a task' indicates creating or modifying task metadata by attaching a label.
Attacks that exploit this kind of access
Add a label to a task for categorization. Get available labels with get_labels first. It is categorised as a Write tool in the Nubis MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Nubis MCP server in PolicyLayer and add a rule for add_label_to_task: 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 Nubis. Nothing to install.
add_label_to_task 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 add_label_to_task 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 add_label_to_task. 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.
add_label_to_task is provided by the Nubis MCP server (@lil2good/nubis-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 →