pull_changes · Overleaf MCP Server MCP: Risk & Policy

WHAT IT DOES

What pull_changes does on Overleaf MCP Server

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

WHY IT NEEDS A POLICY

Why pull_changes needs a policy

This tool retrieves remote changes and applies them to local files, which constitutes data modification. While it is a standard, reversible operation (not destructive), it does alter the local project state. The severity is medium because misuse could overwrite local changes or introduce unintended modifications to project files, though this is a normal Git operation with recoverable outcomes.

From the tool's definition Tool description states 'Pull latest changes from Overleaf for a local project', indicating it modifies local project files by synchronizing them with remote state.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

pull_changes Rate-limited

pull_changes 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": {
    "pull_changes": {
      "limits": [
        {
          "counter": "pull_changes_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 MCP Server, so you can run agents against it safely.

FAQ

Questions about pull_changes

What does the pull_changes tool do? +

Pull latest changes from Overleaf for a local project. It is categorised as a Write tool in the Overleaf 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 pull_changes? +

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

What risk level is pull_changes? +

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

Can I rate-limit pull_changes? +

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

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

pull_changes is provided by the Overleaf MCP Server MCP server (juho127/overleafmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.