Execute one GDB command in current active debug session.
AI agents invoke debug_command to trigger actions in Openocd. 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 falls squarely into Execute because it triggers external operations (GDB command execution) whose effects depend entirely on the arguments provided. While GDB commands are typically used for legitimate debugging, they have broad capability to inspect and manipulate running code and memory.
From the tool's definition The tool executes GDB commands ('Execute one GDB command in current active debug session'). GDB is a debugger that can run arbitrary code, inspect and modify memory, set breakpoints, and control program execution.
Documented attack patterns abuse exactly the kind of access debug_command gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Openocd, and nothing reaches the server without passing your rules. This is the rule we recommend for debug_command:
{
"version": "1",
"default": "deny",
"tools": {
"debug_command": {
"limits": [
{
"counter": "debug_command_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}debug_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.
Free to start. No card required.
Execute one GDB command in current active debug session. It is categorised as a Execute tool in the Openocd MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Openocd MCP server in PolicyLayer and add a rule for debug_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 Openocd. Nothing to install.
debug_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 debug_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 debug_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.
debug_command is provided by the Openocd MCP server (luiox/openocd-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Openocd, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
14 Openocd tools catalogued and risk-classified — across an index of 43,000+ MCP servers.