debug_inspect_variable
AI agents call debug_inspect_variable 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.
Inspecting variables during debugging retrieves program state without modifying code, execution flow, or data—a read operation. Severity is medium rather than low because a debugger in an AI agent's hands could expose sensitive data (secrets, PII) embedded in runtime state, though the impact is informational rather than destructive.
From the tool's definition Tool name 'debug_inspect_variable' indicates inspection/retrieval of variable state during debugging. No description provided, but sibling tools (debug_evaluate, debug_evaluate_watches, debug_get_breakpoints) and the debugger's inspection purpose suggest…
Attacks that exploit this kind of access
debug_inspect_variable. 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_inspect_variable: 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_inspect_variable 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_inspect_variable 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_inspect_variable. 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_inspect_variable 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 →