AI agents use switch_run to create or update resources in Yaver — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Yaver environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
id | string | Yes | |
directory | string | — |
Parameters from the server's own tool schema.
An AI agent can call switch_run faster than any human can review — one bad instruction and it creates or modifies resources in Yaver by the hundred, each call as confident as the last.
Risk signalsAccepts file system path (directory)
Attacks that exploit this kind of access
Execute a previously-planned switch. HARD switches emit a rewrite prompt for the AI agent instead of running inline. It is categorised as a Write tool in the Yaver MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
switch_run accepts 2 parameters: id, directory. Required: id. 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 switch_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.
switch_run is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the switch_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 switch_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.
switch_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.