Disconnect debugger client and close session
AI agents invoke disconnect_debugger to trigger actions in MCP Debug Server. 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.
Disconnecting the debugger closes the active session and detaches the debugging client. This is an operational action that triggers an external state change (ending a debug session), which may leave attached processes in an undefined state. It's not purely destructive (no data is deleted), but it executes a session-termination operation with potential side effects on the target process.
From the tool's definition 'Disconnect debugger client and close session' — terminates an active debugging session
Attacks that exploit this kind of access
Disconnect debugger client and close session. It is categorised as a Execute tool in the MCP Debug Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP Debug Server MCP server in PolicyLayer and add a rule for disconnect_debugger: 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 Debug Server. Nothing to install.
disconnect_debugger 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 disconnect_debugger 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 disconnect_debugger. 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.
disconnect_debugger is provided by the MCP Debug Server MCP server (nickzer0/mcp-debugserver). 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 →