Mark all notifications as read for the authenticated user
AI agents use mark_notifications_read to create or update resources in Forgejo — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Forgejo environment.
This tool modifies notification state (read status) for the authenticated user, which is a reversible write operation. It does not execute arbitrary code, delete data permanently, or move money. While it changes state in the system, the scope is limited to the user's own notification preferences and the change is easily reversible (notifications can be marked unread again).
From the tool's definition Tool name 'mark_notifications_read' and description 'Mark all notifications as read for the authenticated user' indicate a state change operation that modifies notification records.
Documented attack patterns abuse exactly the kind of access mark_notifications_read gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Forgejo, and nothing reaches the server without passing your rules. This is the rule we recommend for mark_notifications_read:
{
"version": "1",
"default": "deny",
"tools": {
"mark_notifications_read": {
"limits": [
{
"counter": "mark_notifications_read_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}mark_notifications_read 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.
Mark all notifications as read for the authenticated user. It is categorised as a Write tool in the Forgejo MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Forgejo MCP server in PolicyLayer and add a rule for mark_notifications_read: 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 Forgejo. Nothing to install.
mark_notifications_read 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 mark_notifications_read 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 mark_notifications_read. 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.
mark_notifications_read is provided by the Forgejo MCP server (sqcows/forgejo-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Forgejo, 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.
103 Forgejo tools catalogued and risk-classified — across an index of 43,000+ MCP servers.