File system resource discovery and reading
AI agents call Resources to retrieve information from 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 file system queries and data retrieval operations ('discovery and reading'), which aligns with the Read category. Severity is medium rather than low because uncontrolled file system access could expose sensitive configuration files, secrets, source code, or private data — a significant but not catastrophic risk if an AI agent misuses it by reading files it shouldn't access.
From the tool's definition Tool description states 'File system resource discovery and reading' — these are read operations that retrieve file system information and file contents without modification.
Attacks that exploit this kind of access
File system resource discovery and reading. It is categorised as a Read tool in the MCP Server MCP Server, which means it retrieves data without modifying state.
Register the MCP Server MCP server in PolicyLayer and add a rule for Resources: 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. Nothing to install.
Resources 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 Resources 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 Resources. 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.
Resources is provided by the MCP Server MCP server (krishanu-das-05/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 →