Medium Risk

mark_folder_as_read

Marks all items in a specific folder as read.

How to control mark_folder_as_read ↓

What mark_folder_as_read does on RSS MCP Server

AI agents use mark_folder_as_read 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.

Medium Risk

Why mark_folder_as_read needs a policy

This tool performs a reversible modification of data—changing the read status of articles. It does not delete, destroy, execute arbitrary code, or create financial obligations. The 'medium' severity reflects that bulk state changes across multiple items could affect user workflow if applied incorrectly to the wrong folder, but the action is fully reversible by marking items as unread.

From the tool's definition Tool name 'mark_folder_as_read' and description 'Marks all items in a specific folder as read' indicate a state change operation that modifies item metadata (read status) across multiple items in a folder.

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

How to control mark_folder_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_folder_as_read:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "mark_folder_as_read": {
      "limits": [
        {
          "counter": "mark_folder_as_read_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

mark_folder_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.

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

Free to start. No card required.

Related tools and policies

Go deeper

Questions about mark_folder_as_read

What does the mark_folder_as_read tool do? +

Marks all items in a specific folder 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_folder_as_read? +

Register the RSS MCP Server MCP server in PolicyLayer and add a rule for mark_folder_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_folder_as_read? +

mark_folder_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_folder_as_read? +

Yes. Add a rate_limit block to the mark_folder_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_folder_as_read completely? +

Set action: deny in the PolicyLayer policy for mark_folder_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_folder_as_read? +

mark_folder_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.

Free to start. No card required.

34 RSS MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.