AI agents use add_issue_note to create or update resources in Mantis — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mantis environment.
This tool creates new note content attached to an issue, which modifies the issue record reversibly. It is a Write operation because notes can be edited or deleted by authorized users. The severity is medium because unauthorized note additions could inject false information into issue tracking but the impact is limited to annotation rather than core data corruption or financial consequences.
From the tool's definition Tool name 'add_issue_note' and description '為一個 Mantis 問題新增備註' (Add a note to a Mantis issue) indicates creating/appending new data to an existing issue.
Attacks that exploit this kind of access
為一個 Mantis 問題新增備註. It is categorised as a Write tool in the Mantis MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mantis MCP server in PolicyLayer and add a rule for add_issue_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 Mantis. Nothing to install.
add_issue_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_issue_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_issue_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_issue_note is provided by the Mantis MCP server (mantis-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 →