This record as markdown: /tools/io-github-kivanccakmak-yaver/models-run.md
What models_run does on Yaver
AI agents invoke models_run 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 |
|---|---|---|---|
model | string | Yes | |
prompt | string | Yes | |
system | string | — | System prompt (optional) |
Parameters from the server's own tool schema.
Why models_run is rated High
Running inference on a local model is a form of code/computation execution. While the immediate blast radius may be contained to local inference, a malicious agent could invoke arbitrary models with arbitrary inputs, potentially causing resource exhaustion, triggering side effects via model outputs (e.g., if the model calls external APIs or scripts), or exfiltrating data through the inference process.
From the tool's definition Tool description states 'Quick inference with a local model' — 'inference' with a model is code execution.
Attacks that exploit this kind of access
The rule that runs models_run 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 models_run, this is the rule to start with:
models_run 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 models_run call is checked against it from then on.
Questions about models_run
Quick inference with a local model. 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.
models_run accepts 3 parameters: model, prompt, system. Required: model, prompt. 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 models_run: 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.
models_run 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 models_run 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 models_run. 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.
models_run 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