start_async_windbg_command · Dump Analyzer MCP

WHAT IT DOES

What start_async_windbg_command does on Dump Analyzer

AI agents invoke start_async_windbg_command to trigger actions in Dump Analyzer. 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.

WHY IT NEEDS A POLICY

Why start_async_windbg_command needs a policy

This tool executes external debugger commands (CDB) whose effects depend on the command arguments provided by the AI agent. While the immediate context is crash dump analysis, CDB commands can trigger side effects beyond simple data retrieval.

From the tool's definition Tool 'start_async_windbg_command' starts CDB (Windows debugger) commands asynchronously. CDB commands can execute arbitrary operations within the debugging context, including code inspection, memory manipulation, and potential system-level effects depending…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

start_async_windbg_command Rate-limited

start_async_windbg_command stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "start_async_windbg_command": {
      "limits": [
        {
          "counter": "start_async_windbg_command_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Dump Analyzer, so you can run agents against it safely.

FAQ

Questions about start_async_windbg_command

What does the start_async_windbg_command tool do? +

Start a CDB command asynchronously and return a command_id. It is categorised as a Execute tool in the Dump Analyzer MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on start_async_windbg_command? +

Register the Dump Analyzer MCP server in PolicyLayer and add a rule for start_async_windbg_command: 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 Dump Analyzer. Nothing to install.

What risk level is start_async_windbg_command? +

start_async_windbg_command is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit start_async_windbg_command? +

Yes. Add a rate_limit block to the start_async_windbg_command 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.

How do I block start_async_windbg_command completely? +

Set action: deny in the PolicyLayer policy for start_async_windbg_command. 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.

What MCP server provides start_async_windbg_command? +

start_async_windbg_command is provided by the Dump Analyzer MCP server (zuohuiyang/dump-analyzer-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.