screenshot_editor
Capture the 2D or 3D editor viewport as a PNG as image content so the assistant can see the scene. The requested viewport's tab must be the ACTIVE main-screen tab, and this tool refuses with viewport_not_active when it is not: a hidden tab's viewport is either a few pixels or a full-size stale fr...
This record as markdown: /tools/breakpoint-mcp/screenshot-editor.md
What screenshot_editor does on Breakpoint
AI agents call screenshot_editor 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 |
|---|---|---|---|
viewport | string | — | Which viewport (default 3d) |
Parameters from the server's own tool schema.
Why screenshot_editor is rated Low
Even though screenshot_editor 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.
Attacks that exploit this kind of access
The rule that runs screenshot_editor 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 screenshot_editor, this is the rule to start with:
screenshot_editor 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 screenshot_editor call is checked against it from then on.
Questions about screenshot_editor
Capture the 2D or 3D editor viewport as a PNG as image content so the assistant can see the scene. The requested viewport's tab must be the ACTIVE main-screen tab, and this tool refuses with viewport_not_active when it is not: a hidden tab's viewport is either a few pixels or a full-size stale frame that looks exactly like a good capture. It also refuses with window_not_drawing when the editor window is off screen or headless: Godot draws nothing then. A fresh editor is on the 3D tab and opening a scene does NOT switch it, so to capture 2d call main_screen_set {"name":"2D"} first AND pass {"viewport":"2d"} — the default is 3d, so switching the tab alone captures the tab you just left. main_screen_get reports which tab is active. It is categorised as a Read tool in the Breakpoint MCP Server, which means it retrieves data without modifying state.
screenshot_editor accepts 1 parameter: viewport. 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 screenshot_editor: 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.
screenshot_editor 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 screenshot_editor 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 screenshot_editor. 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.
screenshot_editor 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