Get scopes (locals, globals) for a frame.
AI agents call debug_get_scopes 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 debugging information (local and global variables) from a specific stack frame during a debug session. It performs no modification, deletion, or execution of code—it only queries and returns scope data. While it could expose sensitive information if the debugged program contains secrets, the tool itself is purely informational.
From the tool's definition Tool name 'debug_get_scopes' and description 'Get scopes (locals, globals) for a frame' indicate retrieval of variable scope information without modification.
Attacks that exploit this kind of access
Get scopes (locals, globals) for a frame. 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_scopes: 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_scopes 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_scopes 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_scopes. 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_scopes 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 →