AI agents use mark_feed_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.
This tool creates a reversible modification to feed item metadata (read status). It does not delete data (so not Destructive), does not execute code (not Execute), does not move money (not Financial), and is more impactful than a simple Read operation.
From the tool's definition Tool performs 'mark_feed_read' which modifies state by marking all items in a feed as read. The description explicitly states it marks items, which is a write operation that changes data (read status).
Risk signalsBulk/mass operation — affects multiple targets
Documented attack patterns abuse exactly the kind of access mark_feed_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_feed_read:
{
"version": "1",
"default": "deny",
"tools": {
"mark_feed_read": {
"limits": [
{
"counter": "mark_feed_read_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}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.
Free to start. No card required.
Mark all items in a feed 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_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 FreshRSS 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 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.