Combined trace: runs get_pc, localize $lr, and my_bt2 in one command.
AI agents invoke switch_print_trace to trigger actions in Gdb Multiarch. 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 tool executes multiple GDB commands (get_pc, localize, my_bt2) against a live debugging target. Executing commands in a GDB session can affect program state, trigger side effects in the debugged process, or interfere with execution flow.
From the tool's definition 'runs get_pc, localize $lr, and my_bt2 in one command' — executes multiple GDB commands/functions in sequence within a live debugging session
Attacks that exploit this kind of access
Combined trace: runs get_pc, localize $lr, and my_bt2 in one command. It is categorised as a Execute tool in the Gdb Multiarch MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Gdb Multiarch MCP server in PolicyLayer and add a rule for switch_print_trace: 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 Gdb Multiarch. Nothing to install.
switch_print_trace 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 switch_print_trace 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 switch_print_trace. 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.
switch_print_trace is provided by the Gdb Multiarch MCP server (sbergeron42/gdb-multiarch-mcp). 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 →