AI agents call list_functions to retrieve information from Jlink without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns function symbol metadata from an ELF binary file. It performs no writes, deletions, code execution, or side effects. It is purely a read operation that assists debugging by providing symbol information. The low severity reflects minimal blast radius even if misused, as the tool cannot alter system state or trigger external actions.
From the tool's definition Tool name 'list_functions' and description '列出 ELF 文件中所有函数符号' (list all function symbols in ELF file) indicate data retrieval only—reading symbol information from compiled firmware without modification or execution.
Attacks that exploit this kind of access
列出 ELF 文件中所有函数符号。. It is categorised as a Read tool in the Jlink MCP Server, which means it retrieves data without modifying state.
Register the Jlink MCP server in PolicyLayer and add a rule for list_functions: 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 Jlink. Nothing to install.
list_functions 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_functions 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_functions. 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_functions is provided by the Jlink MCP server (xun123456/jlink-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 →