AI agents call inspect_file to retrieve information from Demo without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays file metadata and content previews. It has no side effects—it does not create, modify, delete, or execute anything. The operation is purely informational, making it a Read category tool with low severity since file metadata and previews are typically non-sensitive in controlled environments and misuse would only expose data rather than cause destructive harm.
From the tool's definition Tool name 'inspect_file' and description 'Return file metadata and content preview' indicate retrieval of file information and preview content without modification or deletion.
Attacks that exploit this kind of access
Return file metadata and content preview for text/csv/image workflows. It is categorised as a Read tool in the Demo MCP Server, which means it retrieves data without modifying state.
Register the Demo MCP server in PolicyLayer and add a rule for inspect_file: 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 Demo. Nothing to install.
inspect_file 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 inspect_file 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 inspect_file. 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.
inspect_file is provided by the Demo MCP server (penguinszp001/mcp-server-demo). 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 →