browser_type

Focus an element by snapshot ref (e.g., 's1e5' for main frame or 's1f2e10' for iframe elements), type text/keys. Returns: (1) shortened YAML snapshot text, (2) base64 PNG screenshot, (3) base64 PNG screenshot with refs. Note: Snapshot is shortened by default. If you see an element in the screensh...

Server Search search-mcp-server
Category Execute
Risk class High
Parameters 41 required

What browser_type does on Search

AI agents invoke browser_type to trigger actions in Search. 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.

ParameterTypeRequiredDescription
text string Text to type. Embed key presses with <kbd>…</kbd>, e.g., "Hello <kbd>Enter</kbd>". Supported keys: Meta (platform-aware: Cmd on macOS, Ctrl on Windows/Linux), A
clear boolean Whether to clear the existing value before typing. Default: true
submit boolean Convenience flag to press Enter after typing
target string Yes Element target: snapshot ref such as "s1e1" for main frame or "s1f2e5" for iframe elements (coordinates are also accepted).

Parameters from the server's own tool schema.

Why browser_type needs a policy

This tool executes browser automation actions by typing text or key sequences into focused elements on a live web page. It can be misused to submit forms, enter credentials, trigger searches, or interact with any input field — effects depend entirely on the target element and page context, making it an Execute-category tool with high severity due to potential for broad unintended actions.

From the tool's definition Focus an element by snapshot ref, type text/keys — triggers keyboard input interactions in a live browser session

Questions about browser_type

What does the browser_type tool do? +

Focus an element by snapshot ref (e.g., 's1e5' for main frame or 's1f2e10' for iframe elements), type text/keys. Returns: (1) shortened YAML snapshot text, (2) base64 PNG screenshot, (3) base64 PNG screenshot with refs. Note: Snapshot is shortened by default. If you see an element in the screenshot that has no ref in the snapshot, call browser_snapshot with detail='all' to get the full snapshot. Warning: Snapshot may not reflect latest page state due to async web content; call browser_snapshot to get current state if needed. It is categorised as a Execute tool in the Search MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

What parameters does browser_type accept? +

browser_type accepts 4 parameters: text, clear, submit, target. Required: target. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on browser_type? +

Register the Search MCP server in PolicyLayer and add a rule for browser_type: 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 Search. Nothing to install.

What risk level is browser_type? +

browser_type is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit browser_type? +

Yes. Add a rate_limit block to the browser_type 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.

How do I block browser_type completely? +

Set action: deny in the PolicyLayer policy for browser_type. 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.

What MCP server provides browser_type? +

browser_type is provided by the Search MCP server (search-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// LOOK UP ANOTHER 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 →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.