Returns the list of files that should never be modified without explicit confirmation
AI agents call get_protected_files to retrieve information from Ginialtech without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns information about protected files but does not modify, delete, or execute any operations. It is purely informational, helping AI agents understand which files require confirmation before modification. The retrieval of this metadata poses minimal security risk.
From the tool's definition Tool name is 'get_protected_files' and description states it 'Returns the list of files' — a retrieval operation with no side effects.
Attacks that exploit this kind of access
Returns the list of files that should never be modified without explicit confirmation. It is categorised as a Read tool in the Ginialtech MCP Server, which means it retrieves data without modifying state.
Register the Ginialtech MCP server in PolicyLayer and add a rule for get_protected_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 Ginialtech. Nothing to install.
get_protected_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 get_protected_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 get_protected_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.
get_protected_files is provided by the Ginialtech MCP server (marcelaborgarello/ginialteach-mcp). 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 →