mark_feed_as_read

THE RISK

Medium Risk

Why mark_feed_as_read needs a policy

This tool creates or modifies data reversibly by changing the read status of feed items. While the modification is metadata-level rather than destructive, it alters application state in a way that affects user experience (marking items as read cannot be undone via this tool alone, but the underlying data is not deleted or overwritten).

From the tool's definition Tool name 'mark_feed_as_read' and description 'Marks all items in a specific feed as read' indicate modification of feed item state/metadata.

Documented attack patterns abuse exactly the kind of access mark_feed_as_read gives an agent:

POLICY

How to control mark_feed_as_read

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_feed_as_read:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "mark_feed_as_read": {
      "limits": [
        {
          "counter": "mark_feed_as_read_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

mark_feed_as_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.

Create a free account and register RSS MCP Server — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More RSS MCP Server tools

Destructive delete_folder Deletes a folder. This does not delete the feeds within the folder. Destructive delete_subscription Deletes one or more feed subscriptions. Write cancel_article_sharing Cancels sharing for a specific article. Write remove_tag_from_all_articles Removes a tag from all articles that have it. Write remove_tag_from_item Removes a specific tag from an article. Write share_article Marks a specific article as a shared item. Write add_subscription Adds a new feed subscription. Write add_tag_to_item Adds a single tag to a specific article.

All 34 RSS MCP Server tools →

Write tools on other servers

M-Team MCP Server download_torrent YouTube MCP Server generate_video_title Android Forensics ADB MCP Server combine_reports 0xarchive web3_signup

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Argument validation → Checking tool call arguments against schema and policy before they run.
Scoped token → Per-person credentials that grant a defined subset of servers and tools.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about mark_feed_as_read

What does the mark_feed_as_read tool do? +

Marks all items in a specific feed as read. 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.

How do I enforce a policy on mark_feed_as_read? +

Register the RSS MCP Server MCP server in PolicyLayer and add a rule for mark_feed_as_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 RSS MCP Server. Nothing to install.

What risk level is mark_feed_as_read? +

mark_feed_as_read is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit mark_feed_as_read? +

Yes. Add a rate_limit block to the mark_feed_as_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.

How do I block mark_feed_as_read completely? +

Set action: deny in the PolicyLayer policy for mark_feed_as_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.

What MCP server provides mark_feed_as_read? +

mark_feed_as_read is provided by the RSS MCP Server MCP server (xueli-sherryli/rss-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every RSS MCP Server tool call.

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.

CHECK YOUR STACK →