Get call stack frames.
AI agents call debug_get_stacktrace to retrieve information from Polybugger without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves the call stack (a list of function/method frames) from a debugger session. It has no side effects—it only queries and returns information about the execution state of a debugged process. Even though it operates in a debugging context, it performs a passive inspection operation analogous to 'get' or 'fetch', which is the hallmark of the Read category.
From the tool's definition Tool name 'debug_get_stacktrace' and description 'Get call stack frames' indicate a read-only operation that retrieves debugging information without modifying, executing, or deleting any code or data.
Attacks that exploit this kind of access
Get call stack frames. It is categorised as a Read tool in the Polybugger MCP Server, which means it retrieves data without modifying state.
Register the Polybugger MCP server in PolicyLayer and add a rule for debug_get_stacktrace: 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 Polybugger. Nothing to install.
debug_get_stacktrace 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 debug_get_stacktrace 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 debug_get_stacktrace. 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.
debug_get_stacktrace is provided by the Polybugger MCP server (wilfoa/polybugger-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 →