runner_model_probe
Probe which models the installed runner's LOGIN can actually run, by attempting a real generation for each. Use this instead of assuming from a model id — a subscription login refuses models an API key allows, and the set changes without notice. Returns usable/rejected verdicts plus a recommended...
This record as markdown: /tools/io-github-kivanccakmak-yaver/runner-model-probe.md
What runner_model_probe does on Yaver
AI agents invoke runner_model_probe to trigger actions in Yaver. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
| Parameter | Type | Required | Description |
|---|---|---|---|
models | array | — | Model ids to probe; omit for the built-in candidate set |
runner | string | — | Runner to probe (codex today) |
Parameters from the server's own tool schema.
Why runner_model_probe is rated High
This tool triggers external API calls to test model availability by running actual generations. While the intent is informational (probing capabilities), the mechanism involves executing real operations against potentially billable services, which could consume credits or resources. This goes beyond Read (which would be checking metadata) into Execute territory.
From the tool's definition The tool "attempts a real generation for each" model, which means it executes actual API calls and model inference operations. This is not merely reading metadata but performing real computational operations.
Attacks that exploit this kind of access
The rule that runs runner_model_probe safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Yaver, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For runner_model_probe, this is the rule to start with:
runner_model_probe stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Yaver, apply this rule, and every runner_model_probe call is checked against it from then on.
Questions about runner_model_probe
Probe which models the installed runner's LOGIN can actually run, by attempting a real generation for each. Use this instead of assuming from a model id — a subscription login refuses models an API key allows, and the set changes without notice. Returns usable/rejected verdicts plus a recommended default. It is categorised as a Execute tool in the Yaver MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
runner_model_probe accepts 2 parameters: models, runner. The full parameter table on this page comes from the server's own tool schema.
Register the Yaver MCP server in PolicyLayer and add a rule for runner_model_probe: 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 Yaver. Nothing to install.
runner_model_probe is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the runner_model_probe 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 runner_model_probe. 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.
runner_model_probe is provided by the Yaver MCP server (yaver-cli). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Yaver, and thousands of servers like it.
Across the catalogue