在所有JS脚本中搜索关键词/正则表达式，定位加密相关代码
AI agents call js_search_in_scripts to retrieve information from Js Reverse without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a search and analysis tool that queries JavaScript content to find patterns and locate code sections. It performs read-only introspection of existing scripts with no side effects, data modification, or code execution. While it operates in a security/CTF context, the tool itself merely retrieves and searches information, making it a Read category operation with low severity.
From the tool's definition Tool description states '搜索关键词/正则表达式' (search keywords/regular expressions) in JS scripts to 'locate encryption-related code'. The verb is search/locate, which retrieves information without modifying or executing anything.
Attacks that exploit this kind of access
在所有JS脚本中搜索关键词/正则表达式，定位加密相关代码. It is categorised as a Read tool in the Js Reverse MCP Server, which means it retrieves data without modifying state.
Register the Js Reverse MCP server in PolicyLayer and add a rule for js_search_in_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. Nothing to install.
js_search_in_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 js_search_in_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 js_search_in_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.
js_search_in_scripts is provided by the Js Reverse MCP server (jenn619/js-reverse-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 →