Liste tous les fichiers dans un dossier
AI agents call lister_fichiers to retrieve information from MCP File Explorer without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only retrieves directory contents and metadata without modifying, executing, or deleting anything. It is a pure query operation that returns information about the filesystem structure, which is read-only in nature. Low severity because listing files has minimal blast radius—an AI agent cannot cause harm through file enumeration alone.
From the tool's definition Tool name 'lister_fichiers' (list files) and description 'Liste tous les fichiers dans un dossier' (List all files in a folder) indicate a file listing/enumeration operation with no data modification.
Attacks that exploit this kind of access
Liste tous les fichiers dans un dossier. It is categorised as a Read tool in the MCP File Explorer MCP Server, which means it retrieves data without modifying state.
Register the MCP File Explorer MCP server in PolicyLayer and add a rule for lister_fichiers: 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 MCP File Explorer. Nothing to install.
lister_fichiers 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 lister_fichiers 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 lister_fichiers. 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.
lister_fichiers is provided by the MCP File Explorer MCP server (meima-ely/mcp-file-explorer). 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 →