web_preview_start
Start a web dev server (Next.js, Vite, Flutter Web, Expo Web) for a named workspace app. Returns the iframe URL to embed.
This record as markdown: /tools/io-github-kivanccakmak-yaver/web-preview-start.md
What web_preview_start does on Yaver
AI agents invoke web_preview_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 |
|---|---|---|---|
app | string | — | workspace app name |
root | string | — | |
workDir | string | — | absolute project path (when app is empty) |
Parameters from the server's own tool schema.
Why web_preview_start is rated High
This tool initiates and runs code-execution environments (web dev servers). While not destructive or financial, it executes external processes whose behavior depends on the provided arguments (workspace, app name). An agent could misuse this to start unintended servers, consume resources, or expose ports.
From the tool's definition Tool description states it 'Start[s] a web dev server' which triggers external operations (Next.js, Vite, Flutter Web, Expo Web processes). Starting a development server is code execution with effects dependent on the workspace and app specified as arguments.
Attacks that exploit this kind of access
The rule that runs web_preview_start 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_start, this is the rule to start with:
web_preview_start 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_start call is checked against it from then on.
Questions about web_preview_start
Start a web dev server (Next.js, Vite, Flutter Web, Expo Web) for a named workspace app. Returns the iframe URL to embed. 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.
web_preview_start accepts 3 parameters: app, root, workDir. 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 web_preview_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.
web_preview_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 web_preview_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 web_preview_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.
web_preview_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.
More on Yaver, and thousands of servers like it.
Across the catalogue