AI agents call get_symbol_address 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 retrieves memory address information for symbols (functions and global variables) in debugged firmware. It performs a read-only lookup operation without modifying state, executing code, or triggering external actions. The potential blast radius from misuse is minimal—an agent could discover addresses but cannot directly leverage this information to compromise the system without additional tools.
From the tool's definition Tool name 'get_symbol_address' and description '查询符号（函数/全局变量）的内存地址' (query symbol address for functions/global variables) indicate a lookup/retrieval operation with no side effects.
Attacks that exploit this kind of access
查询符号（函数/全局变量）的内存地址。. 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 get_symbol_address: 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.
get_symbol_address 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 get_symbol_address 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 get_symbol_address. 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.
get_symbol_address 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 →