Disk analysis: filesystem usage, inodes, largest directories, I/O stats.
AI agents call sys_disk to retrieve information from RedisNexus without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and analyzes disk usage information without modifying, executing operations, or deleting data. It is a passive monitoring and diagnostic tool that gathers system telemetry. The blast radius of misuse is minimal as it only exposes visibility into disk state, though it could inform an attacker about system capacity or architecture.
From the tool's definition Tool performs disk analysis and reporting functions: 'filesystem usage, inodes, largest directories, I/O stats' — all read-only queries of system metrics.
Attacks that exploit this kind of access
Disk analysis: filesystem usage, inodes, largest directories, I/O stats. It is categorised as a Read tool in the RedisNexus MCP Server, which means it retrieves data without modifying state.
Register the RedisNexus MCP server in PolicyLayer and add a rule for sys_disk: 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 RedisNexus. Nothing to install.
sys_disk 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 sys_disk 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 sys_disk. 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.
sys_disk is provided by the RedisNexus MCP server (rajkumar-madhu/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 →