AI agents use add_issue_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.
This tool creates or modifies data (adds a watcher relationship to an issue) in a reversible manner. It does not delete, destroy, execute arbitrary code, or move money. It falls clearly into the Write category. Severity is low because adding a watcher has minimal blast radius—it only grants notification access and does not alter core issue data or permissions in a harmful way.
From the tool's definition Tool name 'add_issue_watcher' and description 'Add a user as watcher to an issue' indicate creation of a new association between a user and an issue. This modifies issue metadata (watchers list) reversibly.
Documented attack patterns abuse exactly the kind of access add_issue_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_issue_watcher:
{
"version": "1",
"default": "deny",
"tools": {
"add_issue_watcher": {
"limits": [
{
"counter": "add_issue_watcher_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}add_issue_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 a user as watcher to an issue. 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_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 Server. Nothing to install.
add_issue_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_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 add_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.
add_issue_watcher is provided by the Redmine MCP Server MCP server (yonaka15/mcp-server-redmine). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 26 Redmine MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
26 Redmine MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.