Mark an RSS item with a specific action via the Fever API.
AI agents use mark_item to create or update resources in RSS MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your RSS MCP Server environment.
This is a Write operation because it reversibly updates RSS item metadata (read status, saved status, etc.) without deleting data or executing arbitrary code. Severity is medium because misuse could spam status changes across feeds or manipulate user reading history, but changes are reversible and localized to RSS metadata. High confidence due to explicit 'mark' verb indicating state modification.
From the tool's definition Tool performs 'mark an RSS item with a specific action' - a modification operation that changes state (e.g., marking as read/unread, saved/unsaved). The Fever API context shows this updates item status reversibly.
Documented attack patterns abuse exactly the kind of access mark_item gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and RSS MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for mark_item:
{
"version": "1",
"default": "deny",
"tools": {
"mark_item": {
"limits": [
{
"counter": "mark_item_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
} mark_item 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 RSS item with a specific action via the Fever API. It is categorised as a Write tool in the RSS MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the RSS MCP Server MCP server in PolicyLayer and add a rule for mark_item: 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 RSS MCP Server. Nothing to install.
mark_item 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 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. 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 is provided by the RSS MCP Server MCP server (weekend-project-space/rss-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from RSS 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 RSS MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.