read_multiple_files
AI agents call read_multiple_files to retrieve information from Filesystem MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Reading files is a Read operation—it queries/retrieves data without modifying, executing, or destroying anything. The filesystem server includes sandboxing and optional read-only mode, further limiting blast radius. Even if multiple files are read, the operation remains non-destructive and informationally contained.
From the tool's definition Tool name 'read_multiple_files' indicates retrieval of file contents. Server description states it 'Supports file reading/writing, directory management, file searching, and text operations' with 'directory sandboxing' to restrict access.
Attacks that exploit this kind of access
read_multiple_files. It is categorised as a Read tool in the Filesystem MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Filesystem MCP 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 Filesystem MCP 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 Filesystem MCP Server MCP server (preston-harrison/fs-mcp-py). 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 →