// MCP TOOL REFERENCE

WEBCLAW TOOLS

21 tools from the Webclaw MCP Server, categorised by risk level.

// ALL 21 WEBCLAW TOOLS

READ 4 tools

Read list_tabs List all open browser tabs Read list_webmcp_tools List all WebMCP tools available on the current page (both native and auto-synthesized) Read page_snapshot Get a compact accessibility tree snapshot of the current page with @ref labels for interactive elements. Read screenshot Capture a screenshot of the current visible tab

WRITE 1 tools

Write select_option Select an option in a dropdown/select element by its @ref

DESTRUCTIVE 1 tools

Destructive close_tab Close a browser tab

EXECUTE 15 tools

Execute drop_files Drop files onto an element (file input or drag-and-drop target) for uploading Execute hover Hover over an element to trigger mouseover events and reveal hidden UI (e.g., dropdown menus, tooltips) Execute invoke_webmcp_tool Invoke a WebMCP tool declared by the current page Execute navigate_to Navigate the browser to a URL Execute new_tab Open a new browser tab Execute wait_for_navigation Wait for the current page to finish loading Execute click Click an element identified by its @ref from the latest page snapshot Execute evaluate Evaluate a JavaScript expression in the page context and return the result. Execute go_back Navigate back in browser history Execute go_forward Navigate forward in browser history Execute handle_dialog Handle a native browser dialog (alert/confirm/prompt). Use this when a dialog is blocking page interaction. Execute reload Reload the current page Execute scroll_page Scroll the page or scroll to a specific element Execute switch_tab Switch to a specific browser tab Execute type_text Type text into an input element identified by its @ref

// FAQ

How many tools does the Webclaw MCP server have? +

The Webclaw MCP server exposes 21 tools across 4 categories: Read, Write, Destructive, Execute.

How do I enforce policies on Webclaw tools? +

Route the Webclaw 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 Webclaw tools fall into? +

Webclaw tools are categorised as Read (4), Write (1), Destructive (1), Execute (15). Each category has a recommended default policy.

Enforce policy on every Webclaw tool call.

Start from Webclaw, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →

Free to start. No card required.

43,000+ MCP servers and 220,000+ tools scanned and risk-classified.