runtime_assert_screen_text
Assert that on-screen text is present (or absent) by scanning visible Control text in the LIVE scene tree (read-only; no OCR). Sees text on Label / RichTextLabel / Button / LineEdit / TextEdit / CheckBox / LinkButton and similar; does NOT see text drawn directly to the canvas or baked into textures.
This record as markdown: /tools/breakpoint-mcp/runtime-assert-screen-text.md
What runtime_assert_screen_text does on Breakpoint
AI agents call runtime_assert_screen_text 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. |
text | string | Yes | Text (or regular expression) to look for |
regex | boolean | — | Treat `text` as a regular expression (default false = substring) |
present | boolean | — | Assert the text IS present (default true); set false to assert it is absent |
min_count | integer | — | Require at least this many matches (implies present) |
case_sensitive | boolean | — | Case-sensitive match (default false) |
Parameters from the server's own tool schema.
Why runtime_assert_screen_text is rated Low
This tool only reads and validates the state of on-screen text elements. It performs no modifications, deletions, code execution, or financial operations. The read-only nature and assertion-based functionality clearly place it in the Read category with low severity.
From the tool's definition The tool "Assert that on-screen text is present (or absent) by scanning visible Control text in the LIVE scene tree (read-only; no OCR)." explicitly states it is "read-only" and performs assertion checks on existing screen text without modifying or deleting…
Attacks that exploit this kind of access
The rule that runs runtime_assert_screen_text 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_assert_screen_text, this is the rule to start with:
runtime_assert_screen_text 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_assert_screen_text call is checked against it from then on.
Questions about runtime_assert_screen_text
Assert that on-screen text is present (or absent) by scanning visible Control text in the LIVE scene tree (read-only; no OCR). Sees text on Label / RichTextLabel / Button / LineEdit / TextEdit / CheckBox / LinkButton and similar; does NOT see text drawn directly to the canvas or baked into textures. It is categorised as a Read tool in the Breakpoint MCP Server, which means it retrieves data without modifying state.
runtime_assert_screen_text accepts 6 parameters: peer, text, regex, present, min_count, case_sensitive. Required: text. 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_assert_screen_text: 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_assert_screen_text 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_assert_screen_text 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_assert_screen_text. 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_assert_screen_text 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