mark_read_tool · MCP Feed Reader MCP: Risk & Policy

WHAT IT DOES

What mark_read_tool does on MCP Feed Reader

AI agents use mark_read_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_read_tool needs a policy

This tool modifies data (entry read status) but does so reversibly—marking entries as unread is typically possible. It does not delete data, execute code, move money, or trigger external operations. Therefore it falls under Write category. Severity is low because changing read status has minimal blast radius; it only affects the user's interaction state with feed entries, not data integrity or external systems.

From the tool's definition Tool name 'mark_read_tool' and description 'Mark entries as read' indicate modification of entry state/metadata. The action changes the read status of feed entries, which is a reversible state change stored in the SQLite backend.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

mark_read_tool Rate-limited

mark_read_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_read_tool": {
      "limits": [
        {
          "counter": "mark_read_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_read_tool

What does the mark_read_tool tool do? +

Mark entries as read. 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_read_tool? +

Register the MCP Feed Reader MCP server in PolicyLayer and add a rule for mark_read_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_read_tool? +

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

Can I rate-limit mark_read_tool? +

Yes. Add a rate_limit block to the mark_read_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_read_tool completely? +

Set action: deny in the PolicyLayer policy for mark_read_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_read_tool? +

mark_read_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.