class_reference
Full engine-class reference via ClassDB: method SIGNATURES (return type + typed args), signal signatures, and typed properties — the detailed view classdb_get_class summarises as bare names. Read-only. Includes the canonical online docs URL. Pass member to filter to a single method/property/signal.
This record as markdown: /tools/breakpoint-mcp/class-reference.md
What class_reference does on Breakpoint
AI agents call class_reference 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 |
|---|---|---|---|
member | string | — | Only return members whose name contains this substring |
class_name | string | Yes | Engine class name, e.g. AudioStreamPlayer3D |
include_inherited | boolean | — | Include inherited members (default false) |
Parameters from the server's own tool schema.
Why class_reference is rated Low
This tool retrieves and queries class reference information from ClassDB without any ability to modify, create, delete, or execute code. It is a documentation/reference lookup capability that returns structured metadata about methods, signals, and properties. The explicit "Read-only" designation and the nature of returning signatures and properties confirm this is a safe read operation with no side effects.
From the tool's definition The tool is described as "Read-only" and "provides full engine-class reference", "method signatures", "signal signatures", and "typed properties" which are retrieval operations with no modification capability.
Attacks that exploit this kind of access
The rule that runs class_reference 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 class_reference, this is the rule to start with:
class_reference 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 class_reference call is checked against it from then on.
Questions about class_reference
Full engine-class reference via ClassDB: method SIGNATURES (return type + typed args), signal signatures, and typed properties — the detailed view classdb_get_class summarises as bare names. Read-only. Includes the canonical online docs URL. Pass member to filter to a single method/property/signal. It is categorised as a Read tool in the Breakpoint MCP Server, which means it retrieves data without modifying state.
class_reference accepts 3 parameters: member, class_name, include_inherited. Required: class_name. 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 class_reference: 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.
class_reference 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 class_reference 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 class_reference. 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.
class_reference 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