AI agents call list_files 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 is a pure read operation that enumerates files in a project. It has no side effects, does not modify, delete, execute code, or affect financial systems. The blast radius of misuse is minimal—an AI agent querying file lists poses no significant risk to the Overleaf project or user data.
From the tool's definition Tool name 'list_files' and description 'Returns the file tree of the currently open project as a flat list of project-relative paths' indicate it retrieves and queries directory structure without modifying data.
Attacks that exploit this kind of access
Returns the file tree of the currently open project as a flat list of project-relative paths. 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_files: 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_files 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_files 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_files. 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_files 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 →