Start a yaver autoideas run on a local project. Long-lived loop that asks the AI for fresh single-PR-sized ideas every tick and appends them as - [ ] <title> lines to ideas.md (or --output). Mobile/web renders them as checkboxes the user can use as a prompt source for /tasks runs.
AI agents invoke autoideas_start 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 |
|---|---|---|---|
load | string | — | |
tick | integer | — | |
hours | string | — | |
engine | string | — | |
harden | string | — | |
output | string | — | default ideas.md |
prompt | string | — | |
project | string | — | |
work_dir | string | Yes | |
max_batches | integer | — |
Parameters from the server's own tool schema.
autoideas_start triggers real processes with real consequences. An agent gone sideways doesn't fire it once — it starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.
Risk signalsHigh parameter count (10 properties) · Bulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Start a yaver autoideas run on a local project. Long-lived loop that asks the AI for fresh single-PR-sized ideas every tick and appends them as - [ ] <title> lines to ideas.md (or --output). Mobile/web renders them as checkboxes the user can use as a prompt source for /tasks runs. 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.
autoideas_start accepts 10 parameters: load, tick, hours, engine, harden, output, prompt, project, work_dir, max_batches. Required: work_dir. 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 autoideas_start: 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.
autoideas_start 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 autoideas_start 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 autoideas_start. 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.
autoideas_start 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.