Lists all JavaScript scripts loaded in the current page. Returns script ID, URL, and source map information. Use this to find scripts before setting breakpoints or searching. Script IDs are valid for the current page load only; after navigation, call list_scripts again or prefer script URLs for f...
AI agents call list_scripts to retrieve information from JS Reverse MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a passive information retrieval tool used for discovery and analysis. It queries the page's loaded scripts and returns metadata to help the user navigate debugging tasks. While it could support reconnaissance in a security context, the tool itself performs no writes, executions, or destructive operations. It fits the 'Read' category as a search/list operation analogous to examining a page's static properties.
From the tool's definition Tool 'list_scripts' returns information about scripts (script ID, URL, source map information) with no modification, deletion, or execution capability.
Attacks that exploit this kind of access
Lists all JavaScript scripts loaded in the current page. Returns script ID, URL, and source map information. Use this to find scripts before setting breakpoints or searching. Script IDs are valid for the current page load only; after navigation, call list_scripts again or prefer script URLs for follow-up tools. It is categorised as a Read tool in the JS Reverse MCP MCP Server, which means it retrieves data without modifying state.
Register the JS Reverse MCP server in PolicyLayer and add a rule for list_scripts: 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 JS Reverse MCP. Nothing to install.
list_scripts 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_scripts 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_scripts. 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_scripts is provided by the JS Reverse MCP server (zhizhuodemao/js-reverse-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.