mark_unread_tool · MCP Feed Reader MCP: Risk & Policy

WHAT IT DOES

What mark_unread_tool does on MCP Feed Reader

AI agents use mark_unread_tool to create or update resources in MCP Feed Reader — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Feed Reader environment.

WHY IT NEEDS A POLICY

Why mark_unread_tool needs a policy

This tool modifies data (marking an entry's read status) in a reversible manner. The action can be undone by marking it read again. It does not delete, destroy, or execute code—it simply updates a boolean or status field in the SQLite backend. This is a classic Write operation with minimal blast radius.

From the tool's definition Tool name 'mark_unread_tool' and description 'Mark an entry as unread' indicate a state change operation on feed entries.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

mark_unread_tool Rate-limited

mark_unread_tool 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.

View as policy code

policy.json

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

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches MCP Feed Reader, so you can run agents against it safely.

FAQ

Questions about mark_unread_tool

What does the mark_unread_tool tool do? +

Mark an entry as unread. It is categorised as a Write tool in the MCP Feed Reader 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_unread_tool? +

Register the MCP Feed Reader MCP server in PolicyLayer and add a rule for mark_unread_tool: 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 MCP Feed Reader. Nothing to install.

What risk level is mark_unread_tool? +

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

Can I rate-limit mark_unread_tool? +

Yes. Add a rate_limit block to the mark_unread_tool 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_unread_tool completely? +

Set action: deny in the PolicyLayer policy for mark_unread_tool. 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_unread_tool? +

mark_unread_tool is provided by the MCP Feed Reader MCP server (pypi:mcp-feed-reader-crunchtools). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.