dbg_data_breakpoints
Set (replace) data breakpoints — 'watchpoints' that halt when a variable's value changes (DAP dataBreakpointInfo + setDataBreakpoints). Pass watch as a list of { name, variables_ref?, access_type? }: each name is resolved to a dataId via dataBreakpointInfo, then every resolvable id is armed in on...
This record as markdown: /tools/breakpoint-mcp/dbg-data-breakpoints.md
What dbg_data_breakpoints does on Breakpoint
AI agents call dbg_data_breakpoints to retrieve information from Breakpoint without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
watch | array | — | Variables to watch; omit or [] to clear all data breakpoints |
Parameters from the server's own tool schema.
Why dbg_data_breakpoints is rated Low
Even though dbg_data_breakpoints only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
The rule that runs dbg_data_breakpoints safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Breakpoint, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For dbg_data_breakpoints, this is the rule to start with:
dbg_data_breakpoints is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Breakpoint, apply this rule, and every dbg_data_breakpoints call is checked against it from then on.
Questions about dbg_data_breakpoints
Set (replace) data breakpoints — 'watchpoints' that halt when a variable's value changes (DAP dataBreakpointInfo + setDataBreakpoints). Pass watch as a list of { name, variables_ref?, access_type? }: each name is resolved to a dataId via dataBreakpointInfo, then every resolvable id is armed in one setDataBreakpoints call. The result reports the armed breakpoints (each with its resolved data_id and verified flag) and any unresolved variables the adapter cannot watch. Requires a running session; NOT gated (it only configures the debugger). Feature-detected: on an adapter that does not advertise supportsDataBreakpoints it returns a clear "unsupported" message without sending any request. Measured: no Godot build this project tests advertises it — 4.3-stable and 4.7-stable both refuse this tool, so on a shipped engine it is unsupported surface today rather than a feature you can reach; see docs/dap_capability_ledger.json. It is categorised as a Read tool in the Breakpoint MCP Server, which means it retrieves data without modifying state.
dbg_data_breakpoints accepts 1 parameter: watch. The full parameter table on this page comes from the server's own tool schema.
Register the Breakpoint MCP server in PolicyLayer and add a rule for dbg_data_breakpoints: 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 Breakpoint. Nothing to install.
dbg_data_breakpoints is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the dbg_data_breakpoints 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 dbg_data_breakpoints. 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.
dbg_data_breakpoints is provided by the Breakpoint MCP server (breakpoint-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Breakpoint, and thousands of servers like it.
This server
Across the catalogue