Inspects a PHP variable
AI agents call inspect_variable to retrieve information from Smart Xdebug without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays information about a PHP variable's current value and properties during a debug session. It does not modify, execute, or delete anything—it only queries the debugger for variable state information. This is a classic Read operation.
From the tool's definition Tool name is 'inspect_variable' with description 'Inspects a PHP variable'. The verb 'inspect' and the action of examining a variable's state constitute read-only operations with no side effects on the application state.
Attacks that exploit this kind of access
Inspects a PHP variable. It is categorised as a Read tool in the Smart Xdebug MCP Server, which means it retrieves data without modifying state.
Register the Smart Xdebug MCP server in PolicyLayer and add a rule for 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 Smart Xdebug. Nothing to install.
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 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 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.
inspect_variable is provided by the Smart Xdebug MCP server (wallter/smart-xdebug-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 →