runtime_assert_perf
Assert that live Performance monitors meet a caller-supplied baseline within tolerance (read-only). Capture the baseline earlier with runtime_get_monitors and pass it back inline. Pass direction is inferred (time/fps is higher-better; every other monitor is lower-better) unless overridden per key.
This record as markdown: /tools/breakpoint-mcp/runtime-assert-perf.md
What runtime_assert_perf does on Breakpoint
AI agents call runtime_assert_perf 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. |
baseline | object | Yes | Monitor key -> baseline value (capture earlier via runtime_get_monitors) |
direction | object | — | Per-key override of the pass direction (defaults: time/fps higher_better, else lower_better) |
tolerance | number | — | Fractional tolerance applied to each comparison (default 0 = exact) |
Parameters from the server's own tool schema.
Why runtime_assert_perf is rated Low
This tool retrieves and validates performance monitor data against a supplied baseline. It has no side effects—it only asserts conditions and reports results. The read-only designation and comparison logic confirm it is a Read category tool with low severity, as misuse would only produce incorrect assertions without affecting system state or data integrity.
From the tool's definition Tool is explicitly described as "read-only" and performs assertion/validation checks against performance baselines.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
The rule that runs runtime_assert_perf 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_perf, this is the rule to start with:
runtime_assert_perf 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_perf call is checked against it from then on.
Questions about runtime_assert_perf
Assert that live Performance monitors meet a caller-supplied baseline within tolerance (read-only). Capture the baseline earlier with runtime_get_monitors and pass it back inline. Pass direction is inferred (time/fps is higher-better; every other monitor is lower-better) unless overridden per key. It is categorised as a Read tool in the Breakpoint MCP Server, which means it retrieves data without modifying state.
runtime_assert_perf accepts 4 parameters: peer, baseline, direction, tolerance. Required: baseline. 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_perf: 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_perf 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_perf 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_perf. 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_perf 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