Set up and use browser automation for this project via the agent-browser CLI. This tool does NOT drive the browser itself. It points you at agent-browser — a fast, native browser-automation CLI built for agents (https://github.com/vercel-labs/agent-browser) — and tells you how to install it (if n...
AI agents invoke browser_eval to trigger actions in Next Devtools. 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 |
|---|---|---|---|
task | string | — |
Parameters from the server's own tool schema.
This tool enables arbitrary browser automation through shell access to agent-browser CLI. While it doesn't directly execute commands, it facilitates the execution of browser actions (clicks, typing, navigation) whose consequences depend on agent arguments.
From the tool's definition 'Set up and use browser automation for this project via the agent-browser CLI' and 'open pages, click, type, screenshot, or capture console errors in a real browser' — these are external operations whose effects depend on what commands the agent executes in…
Attacks that exploit this kind of access
Set up and use browser automation for this project via the agent-browser CLI. This tool does NOT drive the browser itself. It points you at agent-browser — a fast, native browser-automation CLI built for agents (https://github.com/vercel-labs/agent-browser) — and tells you how to install it (if needed) and where to start. You then run its commands directly (you have shell access), which is faster and more capable than proxying automation through MCP. Call this when you need to open pages, click, type, screenshot, or capture console errors in a real browser. It is categorised as a Execute tool in the Next Devtools MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
browser_eval accepts 1 parameter: task. The full parameter table on this page comes from the server's own tool schema.
Register the Next Devtools MCP server in PolicyLayer and add a rule for browser_eval: 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 Next Devtools. Nothing to install.
browser_eval 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 browser_eval 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 browser_eval. 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.
browser_eval is provided by the Next Devtools MCP server (next-devtools-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →