Extract file properties from a local file to use as EPM policy application criteria. SAFE: Only reads file metadata, never executes the file. Returns file name, size, hashes (SHA1/SHA256), and for Windows PE files (.exe, .dll, .msi, etc.) extracts publisher, product name, file version, product ve...
AI agents call inspect_file_for_policy to retrieve information from BeyondTrust EPM MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs pure information retrieval operations on file metadata and structure. It does not modify, delete, execute, or have any side effects. The explicit statement 'never executes the file' and the list of returned data (hashes, metadata, PE header info) confirm it is a safe read operation used to gather criteria for policy application.
From the tool's definition Tool description states it 'Only reads file metadata, never executes the file' and 'Extract file properties' and 'Returns file name, size, hashes'. The operations listed (extract metadata, read hashes, parse PE headers) are all read-only with no side effects.
Attacks that exploit this kind of access
Extract file properties from a local file to use as EPM policy application criteria. SAFE: Only reads file metadata, never executes the file. Returns file name, size, hashes (SHA1/SHA256), and for Windows PE files (.exe, .dll, .msi, etc.) extracts publisher, product name, file version, product version, and other PE header information. Works on both Windows and Linux. It is categorised as a Read tool in the BeyondTrust EPM MCP Server MCP Server, which means it retrieves data without modifying state.
Register the BeyondTrust EPM MCP Server MCP server in PolicyLayer and add a rule for inspect_file_for_policy: 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 BeyondTrust EPM MCP Server. Nothing to install.
inspect_file_for_policy 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_for_policy 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_for_policy. 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_for_policy is provided by the BeyondTrust EPM MCP Server MCP server (wesharris222/btepmmcp). 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 →