AI agents use add_note to create or update resources in Redmine — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Redmine environment.
Adding a comment is a Write operation because it creates new data in the Redmine system without irreversible consequences. Unlike log_time (which records time entries) or update_issue_status (which modifies task state), notes are supplementary information.
From the tool's definition Tool description states it adds a comment (note) to a task: 'Thêm comment (note) vào task'. This creates new data (a comment/note) that is reversible—comments can typically be edited or deleted in task management systems.
Attacks that exploit this kind of access
Thêm comment (note) vào task. It is categorised as a Write tool in the Redmine MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Redmine MCP server in PolicyLayer and add a rule for add_note: 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 Redmine. Nothing to install.
add_note 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_note 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_note. 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_note is provided by the Redmine MCP server (xukaaaa/redmine-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
add_note is one line of Redmine's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →