AI agents use add_action_item_comment to create or update resources in JoeMCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your JoeMCP environment.
Adding a comment modifies an action item by appending text, which is a reversible write operation. It does not execute code, delete data irreversibly, or move money. The blast radius is minimal since comments are non-critical metadata and easily undoable in a construction management system.
From the tool's definition Tool description states 'Add a comment to an action item' — this creates new data (a comment) that is reversible (comments can be edited or deleted).
Attacks that exploit this kind of access
Add a comment to an action item. It is categorised as a Write tool in the JoeMCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Joe MCP server in PolicyLayer and add a rule for add_action_item_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 JoeMCP. Nothing to install.
add_action_item_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_action_item_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_action_item_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_action_item_comment is provided by the Joe MCP server (lumberjack-so/joemcp). 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 →