AI agents call remove_watcher to permanently remove resources in Redmine MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool name strongly implies removing a watcher from an issue, which is a deletion/removal action (removing a subscription/notification association). This is likely irreversible in the sense that the watcher relationship is deleted, though re-adding is possible. Given sibling tool 'add_watcher' exists, this is the inverse operation.
From the tool's definition Tool name 'remove_watcher' — description is empty and uninformative
Documented attack patterns abuse exactly the kind of access remove_watcher gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Redmine MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for remove_watcher:
{
"version": "1",
"default": "deny",
"hide": [
"remove_watcher"
]
}remove_watcher disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
remove_watcher. It is categorised as a Destructive tool in the Redmine MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Redmine MCP Server MCP server in PolicyLayer and add a rule for remove_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 Server. Nothing to install.
remove_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_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_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_watcher is provided by the Redmine MCP Server MCP server (snowild/redmine-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Redmine MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
35 Redmine MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.