AI agents use add_comment 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 creates new data (comments) in the task management system. The action is reversible (comments can typically be edited or deleted in most systems). The blast radius is low because comments are informational and non-critical—adding unwanted comments causes minimal harm, no data loss, and no execution of external code. This is a typical Write operation for a collaborative task management platform.
From the tool's definition add_comment: 'Add a comment to a task for discussion or status updates. Comments are visible to all workspace members.' The verb 'Add' and the function of creating new comment entries indicates data creation.
Attacks that exploit this kind of access
Add a comment to a task for discussion or status updates. Comments are visible to all workspace members. 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_comment: 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_comment 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_comment 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_comment. 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_comment 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 →