获取页面全局作用域中与加密相关的变量和对象
AI agents call runtime_get_global_vars 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 tool retrieves/queries global variables in a browser runtime context. It performs introspection of the JavaScript execution environment to extract cryptographic objects and variables for analysis. No data is modified, executed, deleted, or financial operations are triggered. While used in a security/CTF context, the action itself is purely informational (Read category).
From the tool's definition Tool name 'runtime_get_global_vars' and description '获取页面全局作用域中与加密相关的变量和对象' (Get encryption-related variables and objects from page global scope) indicates retrieval of data from the runtime environment without modification.
Attacks that exploit this kind of access
获取页面全局作用域中与加密相关的变量和对象. 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 runtime_get_global_vars: 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.
runtime_get_global_vars 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 runtime_get_global_vars 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 runtime_get_global_vars. 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.
runtime_get_global_vars 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 →