stateset_mark_notification_read
Marks a notification as read. Use when the user has viewed the notification.
This record as markdown: /tools/stateset-mcp-server/stateset-mark-notification-read.md
What stateset_mark_notification_read does on Stateset
AI agents use stateset_mark_notification_read to create or update resources in Stateset, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Stateset environment.
Why stateset_mark_notification_read is rated Medium
This tool updates notification metadata (read status) without deleting data or causing irreversible effects. The change can be undone by marking the notification as unread. No data is destroyed, no code is executed, and no financial transactions occur. This is a straightforward Write operation with minimal blast radius if misused by an agent.
From the tool's definition Tool description states 'Marks a notification as read' — this modifies state (notification read status) in a reversible manner. The verb 'marks' indicates a state update operation.
Attacks that exploit this kind of access
The rule that runs stateset_mark_notification_read safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Stateset, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For stateset_mark_notification_read, this is the rule to start with:
stateset_mark_notification_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.
The button opens the PolicyLayer dashboard: create your workspace, connect Stateset, apply this rule, and every stateset_mark_notification_read call is checked against it from then on.
Questions about stateset_mark_notification_read
Marks a notification as read. Use when the user has viewed the notification. It is categorised as a Write tool in the Stateset MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Stateset MCP server in PolicyLayer and add a rule for stateset_mark_notification_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 Stateset. Nothing to install.
stateset_mark_notification_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 stateset_mark_notification_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 stateset_mark_notification_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.
stateset_mark_notification_read is provided by the Stateset MCP server (stateset/stateset-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Stateset, and thousands of servers like it.
This server
Across the catalogue