AI agents use add_watcher to create or update resources in Redmine MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Redmine MCP Server environment.
The tool creates or modifies subscription/notification metadata in Redmine by adding a watcher to an issue or project. This is reversible (watchers can be removed), so it does not qualify as Destructive. It does not execute arbitrary code or delete data, so Execute and Destructive are ruled out. It modifies state rather than merely reading it, placing it in Write.
From the tool's definition Tool name 'add_watcher' indicates modification of issue/project monitoring settings. No description provided, but naming pattern aligns with sibling tools like 'assign_issue' and 'add_issue_note' which modify Redmine state.
Documented attack patterns abuse exactly the kind of access add_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 add_watcher:
{
"version": "1",
"default": "deny",
"tools": {
"add_watcher": {
"limits": [
{
"counter": "add_watcher_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}add_watcher stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
add_watcher. It is categorised as a Write tool in the Redmine MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Redmine MCP Server MCP server in PolicyLayer and add a rule for add_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.
add_watcher 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_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 add_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.
add_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.