// MCP TOOL REFERENCE

BROWSER TOOLS

8 tools from the Browser MCP Server, categorised by risk level.

// ALL 8 BROWSER TOOLS

READ 2 tools

Read browser_get_clickable_elements Get the clickable or hoverable or selectable elements on the current page, don Read browser_screenshot Take a screenshot of the current page or a specific element

WRITE 6 tools

Write browser_click Click an element on the page, before using the tool, use Write browser_close Close the browser when the task is done and the browser is not needed anymore Write browser_hover Hover an element on the page, Either Write browser_press_key Press a key on the keyboard Write browser_scroll Scroll the page Write browser_select Select an element on the page with index, Either

// RUNNING THIS SERVER

The managed route: connect Browser through the PolicyLayer gateway — every tool call above is checked against your policy before it runs, with a full audit log.

DIRECT INSTALL (UNMANAGED) npx -y @agent-infra/mcp-server-browser

// FAQ

How many tools does the Browser MCP server have? +

The Browser MCP server exposes 8 tools across 2 categories: Read, Write.

How do I enforce policies on Browser tools? +

Route the Browser server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard — they are enforced on every call before it reaches the server.

What risk categories do Browser tools fall into? +

Browser tools are categorised as Read (2), Write (6). Each category has a recommended default policy.

Let agents act without letting them run wild.

Route your MCP servers through PolicyLayer and every tool call is checked against your policy before it runs — allow, deny, or require approval. Per-identity grants. Full audit log. Live in minutes.

SECURE YOUR MCP →

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.