AI agents call read_comment_thread 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 queries and retrieves existing comment thread data from Overleaf's review panel. It performs no side effects, does not modify data, does not execute code, and does not delete anything. It is purely informational retrieval, making it a Read category tool with low severity since accessing comment history poses minimal risk when misused by an AI agent.
From the tool's definition Tool name 'read_comment_thread' and description 'Fetches the full message history of one thread (all replies with author + timestamp)' indicate data retrieval with no modification or execution.
Attacks that exploit this kind of access
Fetches the full message history of one thread (all replies with author + timestamp). 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 read_comment_thread: 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.
read_comment_thread 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 read_comment_thread 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 read_comment_thread. 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.
read_comment_thread 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 →