List available data files in the data directory.
AI agents call list_data_files to retrieve information from OSRS MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs a directory listing operation, which is a read-only query that returns metadata about available files without altering, executing, or deleting anything. It falls clearly under the Read category (retrieves or queries data; no side effects). The severity is low because exposure of file listings carries minimal risk—it may reveal structure but does not enable modification or execution.
From the tool's definition Tool description states it 'List available data files in the data directory.' This is a retrieval operation with no modification, deletion, or execution capability.
Attacks that exploit this kind of access
List available data files in the data directory. It is categorised as a Read tool in the OSRS MCP Server MCP Server, which means it retrieves data without modifying state.
Register the OSRS MCP Server MCP server in PolicyLayer and add a rule for list_data_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 OSRS MCP Server. Nothing to install.
list_data_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 list_data_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 list_data_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.
list_data_files is provided by the OSRS MCP Server MCP server (joshhmann/mcp-osrs). 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 →