Permanently accepts the specified tracked-change suggestions. The text stays in the doc; the pending-change metadata is cleared. Pass the
AI agents call accept_changes to permanently remove resources in Overleaf — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The word 'permanently' and 'cleared' indicate this action is irreversible — once tracked-change metadata is removed, the review/suggestion history cannot be recovered. This is a destructive operation on document metadata that cannot be undone.
From the tool's definition Permanently accepts the specified tracked-change suggestions... the pending-change metadata is cleared
Attacks that exploit this kind of access
Permanently accepts the specified tracked-change suggestions. The text stays in the doc; the pending-change metadata is cleared. Pass the. It is categorised as a Destructive tool in the Overleaf MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Overleaf MCP server in PolicyLayer and add a rule for accept_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.
accept_changes is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the accept_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 accept_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.
accept_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 →