AI agents call list_comments 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 lists existing comment threads from a project's review panel. It performs a read-only query operation with no side effects, no code execution, and no ability to modify or delete data. The blast radius of misuse is minimal—an agent could at worst access comments that may contain sensitive information, but cannot alter project state or perform irreversible actions.
From the tool's definition Tool name 'list_comments' and description 'Returns all review-panel comment threads' indicate pure data retrieval with no modification, execution, or destructive capability.
Attacks that exploit this kind of access
Returns all review-panel comment threads in the open project, sorted by most recently updated. 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_comments: 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_comments 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_comments 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_comments. 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_comments 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 →