AI agents call read_multiple_files to retrieve information from MCP Filesystem Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves file contents without creating, modifying, deleting, or executing anything. It is a straightforward read operation with no side effects. The low severity reflects that unauthorized file reading, while sensitive, has limited blast radius compared to write, execute, or destructive operations. The high confidence is justified by explicit 'read' terminology and the read-only nature of the operation.
From the tool's definition Tool name is 'read_multiple_files' and description states 'Read multiple files at once.' The verb 'read' and absence of any modification language clearly indicates data retrieval only.
Documented attack patterns abuse exactly the kind of access read_multiple_files gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Filesystem Server, and nothing reaches the server without passing your rules. This is the rule we recommend for read_multiple_files:
{
"version": "1",
"default": "deny",
"tools": {
"read_multiple_files": {}
}
}read_multiple_files is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Read multiple files at once. It is categorised as a Read tool in the MCP Filesystem Server MCP Server, which means it retrieves data without modifying state.
Register the MCP Filesystem Server MCP server in PolicyLayer and add a rule for read_multiple_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 MCP Filesystem Server. Nothing to install.
read_multiple_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 read_multiple_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 read_multiple_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.
read_multiple_files is provided by the MCP Filesystem Server MCP server (safurrier/mcp-filesystem). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 21 MCP Filesystem Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
21 MCP Filesystem Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.