runtime_await_condition
Poll a property on a LIVE node until it satisfies a comparison, or a timeout elapses (read-only verification). op is eq | ne | gt | ge | lt | le (the ordered operators require numeric values). Use this to wait for the running game to reach a state before asserting on it — e.g. wait for hp le 0, t...
This record as markdown: /tools/breakpoint-mcp/runtime-await-condition.md
What runtime_await_condition does on Breakpoint
AI agents call runtime_await_condition 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 |
|---|---|---|---|
op | string | — | Comparison operator (default eq) |
path | string | Yes | Node path (relative to the current scene; '/root/...' absolute allowed) |
peer | string | — | Target a headless peer by id (from runtime_spawn_peers). Omit to address the default running game. |
value | object | — | Value to compare the property against (tagged-Variant form for complex types) |
property | string | Yes | Property to read on each poll |
timeout_ms | integer | — | Maximum time to wait, in ms (default 5000) |
poll_interval_ms | integer | — | Delay between polls, in ms (default 100) |
Parameters from the server's own tool schema.
Why runtime_await_condition is rated Low
This tool retrieves and queries the state of a running game node by polling a property until a condition is met. It performs no writes, deletions, or external operations—only reads properties and performs comparisons. The explicit 'read-only' designation confirms this is a Read category tool. Low severity because polling and waiting on conditions poses minimal risk even if misused.
From the tool's definition Tool description explicitly states 'read-only verification' and 'Poll a property on a LIVE node until it satisfies a comparison'. It performs polling and comparison operations without modifying state.
Risk signalsAccepts file system path (path)
Attacks that exploit this kind of access
The rule that runs runtime_await_condition 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_await_condition, this is the rule to start with:
runtime_await_condition 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_await_condition call is checked against it from then on.
Questions about runtime_await_condition
Poll a property on a LIVE node until it satisfies a comparison, or a timeout elapses (read-only verification). op is eq | ne | gt | ge | lt | le (the ordered operators require numeric values). Use this to wait for the running game to reach a state before asserting on it — e.g. wait for hp le 0, then runtime_assert_screen_text. It is categorised as a Read tool in the Breakpoint MCP Server, which means it retrieves data without modifying state.
runtime_await_condition accepts 7 parameters: op, path, peer, value, property, timeout_ms, poll_interval_ms. Required: path, property. 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_await_condition: 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_await_condition 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_await_condition 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_await_condition. 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_await_condition 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