This record as markdown: /tools/io-github-kivanccakmak-yaver/web-preview-stop.md
What web_preview_stop does on Yaver
AI agents invoke web_preview_stop 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.
Why web_preview_stop is rated High
This tool triggers a state-change operation (stopping a running web preview server). While not destructive in the sense of deleting data, it executes a command that halts an external process. The severity is medium because stopping a development preview impacts the developer's workflow but does not delete data or cause financial harm.
From the tool's definition Tool performs an action that 'stops' an active service ('Stop serving the active web preview'), which is an external operation with side effects that cannot be instantly reversed without user re-invocation.
Attacks that exploit this kind of access
The rule that runs web_preview_stop 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 web_preview_stop, this is the rule to start with:
web_preview_stop 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 web_preview_stop call is checked against it from then on.
Questions about web_preview_stop
Stop serving the active web preview. 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.
Register the Yaver MCP server in PolicyLayer and add a rule for web_preview_stop: 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.
web_preview_stop 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 web_preview_stop 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 web_preview_stop. 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.
web_preview_stop 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