根据函数名提取完整的函数实现代码
AI agents call js_get_function_body 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 (reads) JavaScript source code from a browser environment. While it operates in a security/CTF context where users may be analyzing or reverse-engineering web applications, the tool itself performs no writes, deletions, execution of external commands, financial transactions, or side effects. It simply extracts and returns function definitions.
From the tool's definition Tool name 'js_get_function_body' and description 'extract complete function implementation code based on function name' indicate retrieval of source code without modification.
Attacks that exploit this kind of access
根据函数名提取完整的函数实现代码. 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_get_function_body: 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_get_function_body 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_get_function_body 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_get_function_body. 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_get_function_body 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 →