Remove a watcher from a Redmine issue.
AI agents call remove_issue_watcher to permanently remove resources in Redmine MCP OAuth Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Removing a watcher deletes the association between a user and an issue. While not catastrophic (no data is permanently lost, the watcher can be re-added), the action is a deletion of a record with no built-in undo, placing it in the Destructive category. Severity is medium because the blast radius is limited to issue notification/subscription tracking.
From the tool's definition 'Remove a watcher from a Redmine issue' — removal of a watcher association is an irreversible delete operation on that relationship
Attacks that exploit this kind of access
Remove a watcher from a Redmine issue. It is categorised as a Destructive tool in the Redmine MCP OAuth Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Redmine MCP OAuth Server MCP server in PolicyLayer and add a rule for remove_issue_watcher: 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 MCP OAuth Server. Nothing to install.
remove_issue_watcher is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the remove_issue_watcher 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 remove_issue_watcher. 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.
remove_issue_watcher is provided by the Redmine MCP OAuth Server MCP server (zh/redmine_mcp_py). 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 →