mark_feed_read
Mark all items in a feed as read up to (and including) the given newest item ID.
This record as markdown: /tools/aiquila-nextcloud-mcp-server/mark-feed-read.md
What mark_feed_read does on AIquila — Nextcloud MCP Server
AI agents use mark_feed_read to create or update resources in AIquila — Nextcloud MCP Server, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your AIquila — Nextcloud MCP Server environment.
Why mark_feed_read is rated Medium
The tool modifies the read status of feed items, which is a reversible state change (items can be marked unread again). This is a Write operation rather than Read (it changes state) or Destructive (the change is reversible). The blast radius is minimal since it only affects the user's view state of feed items, with no data loss or external side effects. Severity is low due to limited impact scope.
From the tool's definition Tool name 'mark_feed_read' and description 'Mark all items in a feed as read up to (and including) the given newest item ID' indicates modification of feed state/metadata.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
The rule that runs mark_feed_read safely
PolicyLayer is an MCP gateway: it sits between your AI agents and AIquila — Nextcloud MCP Server, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For mark_feed_read, this is the rule to start with:
mark_feed_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 AIquila — Nextcloud MCP Server, apply this rule, and every mark_feed_read call is checked against it from then on.
Questions about mark_feed_read
Mark all items in a feed as read up to (and including) the given newest item ID. It is categorised as a Write tool in the AIquila — Nextcloud MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the AIquila — Nextcloud MCP Server MCP server in PolicyLayer and add a rule for mark_feed_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 AIquila — Nextcloud MCP Server. Nothing to install.
mark_feed_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_feed_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_feed_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_feed_read is provided by the AIquila — Nextcloud MCP Server MCP server (elgorro/aiquila). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on AIquila — Nextcloud MCP Server, and thousands of servers like it.
This server
Across the catalogue