mark_all_notifications_read
Mark EVERY unread notification in your feed read — account-wide, across all instances, not just one page of list_notifications. Read-state only; it answers nothing. Call list_notifications with unread_only:true first if you need to see what you are clearing: there is no undo.
This record as markdown: /tools/io-github-proagentstore-platform/mark-all-notifications-read.md
What mark_all_notifications_read does on ProAgentStore
AI agents use mark_all_notifications_read to create or update resources in ProAgentStore, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your ProAgentStore environment.
Why mark_all_notifications_read is rated Medium
Modifies notification state across account; reversible via re-sending notifications or manual reversion.
From the tool's definition Mark EVERY unread notification read, no undo
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
The rule that runs mark_all_notifications_read safely
PolicyLayer is an MCP gateway: it sits between your AI agents and ProAgentStore, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For mark_all_notifications_read, this is the rule to start with:
mark_all_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.
The button opens the PolicyLayer dashboard: create your workspace, connect ProAgentStore, apply this rule, and every mark_all_notifications_read call is checked against it from then on.
Questions about mark_all_notifications_read
Mark EVERY unread notification in your feed read — account-wide, across all instances, not just one page of list_notifications. Read-state only; it answers nothing. Call list_notifications with unread_only:true first if you need to see what you are clearing: there is no undo. It is categorised as a Write tool in the ProAgentStore MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the ProAgentStore MCP server in PolicyLayer and add a rule for mark_all_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 ProAgentStore. Nothing to install.
mark_all_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_all_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_all_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_all_notifications_read is provided by the ProAgentStore MCP server (https://mcp.proagentstore.online/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on ProAgentStore, and thousands of servers like it.
This server
Across the catalogue