Starts a new PHP debugging session by listening for XDebug connections and executing a trigger command. WORKFLOW - Call tools in this order: 1. get_session_status - Check if a session is already active 2. set_breakpoint - Set breakpoints at locations you want to inspect 3. start_debug_session - S...
AI agents invoke start_debug_session to trigger actions in Smart Xdebug. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool executes a trigger command to initiate a debugging session, which constitutes triggering external operations (PHP debugging infrastructure). While debugging itself is legitimate, the ability to execute arbitrary trigger commands on a PHP application's runtime creates significant risk if misused by an AI agent—it could be leveraged to inspect sensitive variables, alter execution flow, or probe application…
From the tool's definition Starts a new PHP debugging session by listening for XDebug connections and executing a trigger command; enables runtime inspection and breakpoint control of PHP applications.
Attacks that exploit this kind of access
Starts a new PHP debugging session by listening for XDebug connections and executing a trigger command. WORKFLOW - Call tools in this order: 1. get_session_status - Check if a session is already active 2. set_breakpoint - Set breakpoints at locations you want to inspect 3. start_debug_session - Start the session with your trigger command 4. inspect_variable / control_execution - Debug at breakpoints BEFORE CALLING: - Call get_session_status first. If a session is active, use control_execution with action=. It is categorised as a Execute tool in the Smart Xdebug MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Smart Xdebug MCP server in PolicyLayer and add a rule for start_debug_session: 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.
start_debug_session is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the start_debug_session 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 start_debug_session. 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.
start_debug_session 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 →