Get the list of allowed file system paths.
AI agents call get_allowed_paths to retrieve information from MCP Server Framework without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information about permitted file system paths—a read-only query operation with no side effects. The blast radius is minimal as it only exposes already-known configuration information that would be available through normal security boundary checks. No data is modified, deleted, or executed.
From the tool's definition Tool name 'get_allowed_paths' and description 'Get the list of allowed file system paths' indicate a retrieval operation that queries configuration or metadata without modifying or executing anything.
Attacks that exploit this kind of access
Get the list of allowed file system paths. It is categorised as a Read tool in the MCP Server Framework MCP Server, which means it retrieves data without modifying state.
Register the MCP Server Framework MCP server in PolicyLayer and add a rule for get_allowed_paths: 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 Server Framework. Nothing to install.
get_allowed_paths 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_allowed_paths 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_allowed_paths. 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_allowed_paths is provided by the MCP Server Framework MCP server (tim-akkio/mcp-server). 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 →