Aggregate file usage by extension from a WizTree CSV snapshot.
AI agents call extension_summary 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 retrieves and summarizes information from CSV snapshots without creating, modifying, or deleting any data. It is a classic Read operation (aggregate/summarize query on static data). The low severity reflects minimal blast radius even if misused—an agent could only retrieve disk usage statistics, which poses no destructive, financial, or system-level risk.
From the tool's definition Tool 'extension_summary' performs aggregation and analysis on existing WizTree CSV data. The server is explicitly described as 'Read-only' and this tool 'aggregate[s] file usage by extension', which is a data retrieval and summarization operation with no…
Attacks that exploit this kind of access
Aggregate file usage by extension from a WizTree CSV snapshot. 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 extension_summary: 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.
extension_summary 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 extension_summary 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 extension_summary. 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.
extension_summary 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 →