AI agents call list_tracked_changes to retrieve information from Overleaf without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays information about tracked changes without creating, modifying, deleting, or executing anything. It is a pure query/list operation that has no side effects on the project state. The blast radius of misuse is minimal—an agent could only view pending suggestions, not alter them or execute operations.
From the tool's definition Tool description states it 'Enumerates every pending tracked-change suggestion' and lists metadata (author, email, doc path, op kind).
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Enumerates every pending tracked-change suggestion in the open project (across all docs), with author name + email, doc path, op kind (. It is categorised as a Read tool in the Overleaf MCP Server, which means it retrieves data without modifying state.
Register the Overleaf MCP server in PolicyLayer and add a rule for list_tracked_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. Nothing to install.
list_tracked_changes is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the list_tracked_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.
Set action: deny in the PolicyLayer policy for list_tracked_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.
list_tracked_changes 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.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →