crash_command
Execute a command in the crash utility session
This record as markdown: /tools/42research-dynamic-mcp/crash-command.md
What crash_command does on Dynamic MCP Server
AI agents invoke crash_command to trigger actions in Dynamic MCP 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.
Why crash_command is rated High
This is an Execute tool because it runs commands within a crash utility debugger session, whose effects depend entirely on the argument (the command itself). Crash is a powerful kernel debugging tool that can read/write memory, trigger kernel operations, and inspect system state. Misuse by an AI agent could inspect sensitive kernel data, trigger unintended kernel behavior, or gather information for further attacks.
From the tool's definition Tool executes a command in the crash utility session, which is a debugger that can inspect kernel memory, modify kernel state, and trigger arbitrary operations.
Attacks that exploit this kind of access
The rule that runs crash_command safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Dynamic MCP Server, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For crash_command, this is the rule to start with:
crash_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.
The button opens the PolicyLayer dashboard: create your workspace, connect Dynamic MCP Server, apply this rule, and every crash_command call is checked against it from then on.
Questions about crash_command
Execute a command in the crash utility session. It is categorised as a Execute tool in the Dynamic MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Dynamic MCP Server MCP server in PolicyLayer and add a rule for crash_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 Dynamic MCP Server. Nothing to install.
crash_command 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 crash_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.
Set action: deny in the PolicyLayer policy for crash_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.
crash_command is provided by the Dynamic MCP Server MCP server (42research/dynamic_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Dynamic MCP Server, and thousands of servers like it.
Across the catalogue