runtime_screenshot_diff
Capture the current frame and compare it to a reference PNG at a project path, returning diff stats and a pass/fail vs tolerance (read-only; the diff is computed engine-side so the host stays dependency-free). Establish the reference first by saving a runtime_screenshot as a project asset.
This record as markdown: /tools/breakpoint-mcp/runtime-screenshot-diff.md
What runtime_screenshot_diff does on Breakpoint
AI agents call runtime_screenshot_diff 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. |
region | object | — | Optional sub-region (applied to both frame and reference) to compare |
reference | string | Yes | res:// or user:// path to the reference PNG |
tolerance | number | — | Max fraction of differing pixels that still passes (default 0) |
per_channel_threshold | integer | — | Per-channel delta (0-255) for a pixel to count as different (default 0) |
Parameters from the server's own tool schema.
Why runtime_screenshot_diff is rated Low
This tool retrieves and compares visual data (screenshots) without modifying, creating, or destroying any state. It performs a deterministic analysis operation on existing assets. The 'read-only' designation in the description, combined with the lack of any create/update/delete/execute semantics, clearly categorizes this as a Read operation with minimal security risk.
From the tool's definition Tool description explicitly states 'read-only' and performs comparison/capturing of visual frames. The operation 'Capture the current frame and compare it to a reference PNG' returns 'diff stats and a pass/fail' with no data modification, deletion, or…
Attacks that exploit this kind of access
The rule that runs runtime_screenshot_diff 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_screenshot_diff, this is the rule to start with:
runtime_screenshot_diff 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_screenshot_diff call is checked against it from then on.
Questions about runtime_screenshot_diff
Capture the current frame and compare it to a reference PNG at a project path, returning diff stats and a pass/fail vs tolerance (read-only; the diff is computed engine-side so the host stays dependency-free). Establish the reference first by saving a runtime_screenshot as a project asset. It is categorised as a Read tool in the Breakpoint MCP Server, which means it retrieves data without modifying state.
runtime_screenshot_diff accepts 5 parameters: peer, region, reference, tolerance, per_channel_threshold. Required: reference. 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_screenshot_diff: 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_screenshot_diff 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_screenshot_diff 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_screenshot_diff. 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_screenshot_diff 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