runtime_state_digest
Capture a compact, stable-ordered JSON snapshot of a live subtree's salient state (read-only) — position, rotation, scale, visibility, and modulate by default, or a caller-supplied field list. Deterministic ordering makes it ideal for frame-by-frame comparison alongside runtime_step_frames.
This record as markdown: /tools/breakpoint-mcp/runtime-state-digest.md
What runtime_state_digest does on Breakpoint
AI agents call runtime_state_digest 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 |
|---|---|---|---|
peer | string | — | Target a headless peer by id (from runtime_spawn_peers). Omit to address the default running game. |
root | string | Yes | Root node path in the running scene |
fields | array | — | Property names to capture per node (default: position/global_position/rotation/scale/visible/modulate when present) |
max_depth | integer | — | Max recursion depth (default 8) |
Parameters from the server's own tool schema.
Why runtime_state_digest is rated Low
The tool explicitly states it is read-only and only captures/retrieves state data (position, rotation, scale, visibility, modulate) from a live subtree. No data is modified, created, or deleted. It is purely observational/query-based.
From the tool's definition 'read-only', 'snapshot', 'Capture a compact, stable-ordered JSON snapshot', 'Deterministic ordering makes it ideal for frame-by-frame comparison'
Attacks that exploit this kind of access
The rule that runs runtime_state_digest 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 runtime_state_digest, this is the rule to start with:
runtime_state_digest 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 runtime_state_digest call is checked against it from then on.
Questions about runtime_state_digest
Capture a compact, stable-ordered JSON snapshot of a live subtree's salient state (read-only) — position, rotation, scale, visibility, and modulate by default, or a caller-supplied field list. Deterministic ordering makes it ideal for frame-by-frame comparison alongside runtime_step_frames. It is categorised as a Read tool in the Breakpoint MCP Server, which means it retrieves data without modifying state.
runtime_state_digest accepts 4 parameters: peer, root, fields, max_depth. Required: root. 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 runtime_state_digest: 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.
runtime_state_digest 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 runtime_state_digest 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 runtime_state_digest. 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.
runtime_state_digest 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