mark-notifications-read

THE RISK

Medium Risk

Why mark-notifications-read needs a policy

This tool modifies notification state (marking them as read) but does not delete, destroy, or create new data—it reversibly changes a property. This is a classic Write operation with minimal blast radius. Even if misused by an agent, the worst outcome is marking notifications as read, which is easily reversible by the user through GitHub's interface.

From the tool's definition Tool name 'mark-notifications-read' and description 'Mark GitHub notifications as read' indicate a state modification operation that changes the read/unread status of notifications.

Documented attack patterns abuse exactly the kind of access mark-notifications-read gives an agent:

POLICY

How to control mark-notifications-read

PolicyLayer is an MCP gateway — it sits between your AI agents and GitHub Notifications MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for mark-notifications-read:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "mark-notifications-read": {
      "limits": [
        {
          "counter": "mark-notifications-read_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

mark-notifications-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 GitHub Notifications 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 GitHub Notifications MCP Server tools

Destructive delete-thread-subscription Unsubscribe from a GitHub notification thread Write manage-repo-subscription Manage repository subscription settings including fine-grained notification preferences Write mark-repo-notifications-read Mark GitHub notifications for a specific repository as read Write mark-thread-done Mark a GitHub notification thread as done Write mark-thread-read Mark a GitHub notification thread as read Write set-thread-subscription Subscribe to a GitHub notification thread Read get-thread Get information about a GitHub notification thread Read get-thread-subscription Get subscription status for a GitHub notification thread

All 11 GitHub Notifications 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-notifications-read

What does the mark-notifications-read tool do? +

Mark GitHub notifications as read. It is categorised as a Write tool in the GitHub Notifications 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-notifications-read? +

Register the GitHub Notifications MCP Server MCP server in PolicyLayer and add a rule for mark-notifications-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 GitHub Notifications MCP Server. Nothing to install.

What risk level is mark-notifications-read? +

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

Can I rate-limit mark-notifications-read? +

Yes. Add a rate_limit block to the mark-notifications-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-notifications-read completely? +

Set action: deny in the PolicyLayer policy for mark-notifications-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-notifications-read? +

mark-notifications-read is provided by the GitHub Notifications MCP Server MCP server (mcollina/mcp-github-notifications). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every GitHub Notifications MCP Server tool call.

Start from GitHub Notifications 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 →