reply_comment · Overleaf MCP: Risk & Policy

WHAT IT DOES

What reply_comment does on Overleaf

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

WHY IT NEEDS A POLICY

Why reply_comment needs a policy

This tool creates new data (comment replies) reversibly within an existing thread. It is not destructive since replies can be deleted or edited later. It does not execute code or trigger financial transactions. While it modifies the document's collaborative state, the change is non-destructive and typical of collaborative Write operations.

From the tool's definition Tool description states 'Adds a new message to an existing comment thread', which indicates creating new comment data within Overleaf's collaboration system.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

reply_comment Rate-limited

reply_comment 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": {
    "reply_comment": {
      "limits": [
        {
          "counter": "reply_comment_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 Overleaf, so you can run agents against it safely.

FAQ

Questions about reply_comment

What does the reply_comment tool do? +

Adds a new message to an existing comment thread. Threads come from. It is categorised as a Write tool in the Overleaf MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on reply_comment? +

Register the Overleaf MCP server in PolicyLayer and add a rule for reply_comment: 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 Overleaf. Nothing to install.

What risk level is reply_comment? +

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

Can I rate-limit reply_comment? +

Yes. Add a rate_limit block to the reply_comment 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 reply_comment completely? +

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

reply_comment is provided by the Overleaf MCP server (netique/overleaf-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.