Skip to main content

app_check

This tool on every surface: CLI · MCP · Python · JavaScript · Go · Java · .NET

Check a claim about a recorded session: a model with a fresh context — none of yours — reads the recording (each call, its result or error, and the screen and screenshot after it) through read-only tools, and answers passed, failed or inconclusive with the observations it rests on. Inconclusive means the recording cannot settle it; nothing missing is taken for success. A model's judgment is not proof: keep deterministic assertions (app_wait_for) for what can be asserted directly, and use this for claims about what a person would have seen. Needs no device. The default judge, Claude through the Anthropic API, needs an Anthropic credential and each check is a paid call; it is built but not yet measured against claims with known answers. Judges through "openai:" are measured (docs/guides/verifier.md). A live check is not built yet.

Read-only: readOnlyHint is true.

Arguments​

NameTypeRequiredWhat it is
claimstringyesWhat should be true, precisely: "the terms box was ticked after the tap".
modelstringThe model that judges. Defaults to claude-opus-5-5, not yet measured. "openai:" asks a model through the OpenAI-compatible API: Ollama on this machine by default, with no credential; MOBIUM_AI_BASE_URL names another server, which the recording is then sent to, and MOBIUM_AI_API_KEY its key.
recordstringyesA recording: the .zip app_trace with action stop saved.

Examples​

Each is the arguments of a tools/call request; the first is shown whole.

Ask a model on this machine whether a claim holds in a recording​

{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "app_check",
"arguments": {
"claim": "After card 3 was tapped, it was shown face up as the Blue Morpho.",
"record": "card.zip",
"model": "openai:qwen2.5:14b"
}
}
}