Create a new debugging session. Provide host and port to attach to a running process; omit them for launch mode
AI agents invoke create_debug_session to trigger actions in Mcp Debugger. 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.
Creating a debug session either attaches to a live process or launches a new one. Both actions trigger external operations on running processes, which can intercept execution, inspect memory, and alter program flow. This constitutes execution-level access with high blast radius since an AI agent could misuse debug sessions to manipulate arbitrary processes.
From the tool's definition 'Create a new debugging session' with ability to 'attach to a running process' or 'launch mode'
Attacks that exploit this kind of access
Create a new debugging session. Provide host and port to attach to a running process; omit them for launch mode. It is categorised as a Execute tool in the Mcp Debugger MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Mcp Debugger MCP server in PolicyLayer and add a rule for create_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 Mcp Debugger. Nothing to install.
create_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 create_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 create_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.
create_debug_session is provided by the Mcp Debugger MCP server (@debugmcp/mcp-debugger). 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 →