runtime_step_frames
Advance the running game by an exact number of frames while otherwise frozen, for deterministic, frame-accurate playtesting. DESTRUCTIVE — gated by confirmation. kind selects which loop to tick each step: idle (default), physics, or both. Pair with runtime_time_scale{scale:0} to freeze, then assert.
This record as markdown: /tools/breakpoint-mcp/runtime-step-frames.md
What runtime_step_frames does on Breakpoint
AI agents invoke runtime_step_frames to trigger actions in Breakpoint. 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.
| Parameter | Type | Required | Description |
|---|---|---|---|
kind | string | — | Which loop to tick each step (default idle) |
peer | string | — | Target a headless peer by id (from runtime_spawn_peers). Omit to address the default running game. |
frames | integer | Yes | Number of frames to advance |
confirm | boolean | — | Auto-approve this destructive action (skip the confirmation prompt) |
Parameters from the server's own tool schema.
Why runtime_step_frames is rated High
While the description mentions 'DESTRUCTIVE' and gating by confirmation, the actual operation is advancing game execution state rather than permanently deleting or overwriting data. The tool executes game loop logic with argument-dependent effects, making it Execute rather than Destructive.
From the tool's definition Tool description states it will "Advance the running game by an exact number of frames" and "tick each step" with selectable loop types (idle, physics, or both).
Attacks that exploit this kind of access
The rule that runs runtime_step_frames 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_step_frames, this is the rule to start with:
runtime_step_frames stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. 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_step_frames call is checked against it from then on.
Questions about runtime_step_frames
Advance the running game by an exact number of frames while otherwise frozen, for deterministic, frame-accurate playtesting. DESTRUCTIVE — gated by confirmation. kind selects which loop to tick each step: idle (default), physics, or both. Pair with runtime_time_scale{scale:0} to freeze, then assert. It is categorised as a Execute tool in the Breakpoint MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
runtime_step_frames accepts 4 parameters: kind, peer, frames, confirm. Required: frames. 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_step_frames: 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_step_frames 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 runtime_step_frames 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_step_frames. 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_step_frames 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.
Across the catalogue