AI agents use mark_item_read to create or update resources in FreshRSS MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your FreshRSS MCP Server environment.
Marking items as read is a data modification operation that changes the state of feed items. It is reversible (can be undone by marking unread), so it does not qualify as Destructive. It does not execute code or trigger external operations, so it is not Execute. It modifies existing data rather than just retrieving it, so it is Write.
From the tool's definition Tool name: mark_item_read. Description: 'Mark an item as read'. This modifies state (read/unread status) of existing items in FreshRSS, which is a reversible change. The sibling tool mark_item_unread confirms this is a state-modifying operation.
Documented attack patterns abuse exactly the kind of access mark_item_read gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and FreshRSS MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for mark_item_read:
{
"version": "1",
"default": "deny",
"tools": {
"mark_item_read": {
"limits": [
{
"counter": "mark_item_read_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}mark_item_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 an item as read. It is categorised as a Write tool in the FreshRSS MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the FreshRSS MCP Server MCP server in PolicyLayer and add a rule for mark_item_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 FreshRSS MCP Server. Nothing to install.
mark_item_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_item_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_item_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_item_read is provided by the FreshRSS MCP Server MCP server (rakeshgangwar/freshrss-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from FreshRSS MCP Server, 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.
8 FreshRSS MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.