Select a specific stack frame.
AI agents invoke gdb_select_frame 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.
Selecting a stack frame in GDB changes the debugger's current context, affecting subsequent operations like register reads, variable inspection, and expression evaluation. This is an active operation that manipulates debugger state rather than merely reading data, making it Execute. Misuse could interfere with debugging sessions or cause unintended side effects in subsequent operations.
From the tool's definition Select a specific stack frame
Attacks that exploit this kind of access
Select a specific stack frame. 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 gdb_select_frame: 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.
gdb_select_frame 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 gdb_select_frame 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 gdb_select_frame. 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.
gdb_select_frame 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 →