mark_thread_read · GitHub MCP Server MCP: Risk & Policy

WHAT IT DOES

What mark_thread_read does on GitHub MCP Server

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

WHY IT NEEDS A POLICY

Why mark_thread_read needs a policy

This tool modifies notification metadata (read status) in a reversible manner. It changes the state of a thread from unread to read, which is a Write operation. The blast radius is minimal—changing notification read status does not affect code, data integrity, or system functionality beyond the user's notification preferences.

From the tool's definition Tool name 'mark_thread_read' and description 'Mark a specific notification thread as read' indicate a state-modifying operation that changes the read status of a notification thread.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

mark_thread_read Rate-limited

mark_thread_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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "mark_thread_read": {
      "limits": [
        {
          "counter": "mark_thread_read_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 GitHub MCP Server, so you can run agents against it safely.

FAQ

Questions about mark_thread_read

What does the mark_thread_read tool do? +

Mark a specific notification thread as read. It is categorised as a Write tool in the GitHub 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_thread_read? +

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

What risk level is mark_thread_read? +

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

Can I rate-limit mark_thread_read? +

Yes. Add a rate_limit block to the mark_thread_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_thread_read completely? +

Set action: deny in the PolicyLayer policy for mark_thread_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_thread_read? +

mark_thread_read is provided by the GitHub MCP Server MCP server (software-engineer-mj/github-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.