Compare two WizTree CSV snapshots by path and report the largest changes.
AI agents call compare_csv to retrieve information from WizTree MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs data comparison and analysis on existing CSV snapshots without creating, modifying, deleting, or executing any operations. It retrieves and queries information (largest changes between snapshots) with no side effects. It is consistent with the server's read-only design and falls squarely into the Read category.
From the tool's definition Tool description explicitly states it 'Compare[s] two WizTree CSV snapshots by path and report[s] the largest changes' — a purely analytical operation. Server is described as 'Read-only MCP server' that wraps CSV export for 'disk-usage analysis tools'.
Attacks that exploit this kind of access
Compare two WizTree CSV snapshots by path and report the largest changes. It is categorised as a Read tool in the WizTree MCP MCP Server, which means it retrieves data without modifying state.
Register the WizTree MCP server in PolicyLayer and add a rule for compare_csv: 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 WizTree MCP. Nothing to install.
compare_csv 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 compare_csv 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 compare_csv. 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.
compare_csv is provided by the WizTree MCP server (onmokoworks/wiztree-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 →