Set a breakpoint at a function, file:line, or *address.
AI agents invoke gdb_set_breakpoint 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.
Setting a breakpoint is a debugger control operation that affects execution flow of a running process. It doesn't read, write, or delete data, but it triggers an external side effect (modifying the debug target's execution state). Misuse could interfere with debugging sessions or cause the target process to halt unexpectedly, but it is reversible (breakpoints can be deleted), so it doesn't rise to Destructive.
From the tool's definition Set a breakpoint at a function, file:line, or *address
Attacks that exploit this kind of access
Set a breakpoint at a function, file:line, or *address. 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_set_breakpoint: 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_set_breakpoint 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_set_breakpoint 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_set_breakpoint. 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_set_breakpoint 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 →