// MCP TOOL REFERENCE

CHROME TOOLS

23 tools from the Chrome MCP Server, categorised by risk level.

View the Chrome policy → Token cost: 5,465 tokens →

// ALL 23 CHROME TOOLS

READ 8 tools

Read capture_image Pixel-level visual screenshot (WebP, max 800px, <100KB). Do NOT call this to see what is on the page — call... Read dom_snapshot Structured layout data: bounding boxes, computed styles, paint order, colors. Refs match view_page. Use ONL... Read download Check status of file downloads or list all downloaded files in this session. Downloads happen automatically... Read network_monitor Monitor network requests via CDP. Workflow: start → trigger action → get(pattern: 'api'). Use INSTEAD of ev... Read observe Watch an element for changes over time — use this INSTEAD of writing MutationObserver/setInterval/setTimeou... Read tab_status Active tab's cached URL/title/ready/errors for quick sanity checks mid-workflow ('did my click navigate?').... Read view_page The way to see what is on the page. Call this after navigate/click/switch_tab — not capture_image. Returns ... Read virtual_desk PRIMARY orientation tool — call first in every new session, after reconnect, or when unsure. Lists all tabs...

WRITE 10 tools

Write click Click an element by ref, CSS selector, or viewport coordinates. Dispatches real CDP mouse events (mouseMove... Write configure_session View/set session defaults for recurring parameters (tab, timeout, etc.). Without params: show current defau... Write drag Drag an element via native CDP mouse events (mousePressed → interpolated mouseMoved with buttons:1 → mouseR... Write file_upload Upload file(s) to a file input element. Provide ref or CSS selector to identify the <input type='file'>, an... Write fill_form Fill a complete form with one call — the preferred way to submit any form with 2+ fields. Each field needs ... Write handle_dialog Configure browser dialog handling (alerts, confirms, prompts). Pre-configure BEFORE triggering actions that... Write press_key Press a keyboard key or shortcut. Optionally focus an element first via ref/selector. Use for Enter, Escape... Write scroll Scroll the page, a container, or an element into view. Returns position and content-growth tracking (scroll... Write switch_tab Open a new tab, switch to an existing tab by ID (from virtual_desk), or close a tab. Prefer 'open' over nav... Write type Type text into an input field identified by ref or CSS selector. For multiple fields in the same form, pref...

DESTRUCTIVE 1 tools

Destructive console_logs Retrieve collected browser console logs. Filter by level (info/warning/error/debug) and/or regex pattern. O...

EXECUTE 4 tools

Execute evaluate Execute JavaScript in the browser page context. Good uses: computation, style mutations (.style.X = ..., cl... Execute navigate Navigate the ACTIVE tab to a URL (or action:'back' to go back, action:'reload' to refresh current page — al... Execute run_plan Execute a sequential plan of tool steps server-side. Supports variables ($varName), conditions (if), saveAs... Execute wait_for Wait for a condition: element visible, network idle, or JS expression true

// RUNNING THIS SERVER

The managed route: connect Chrome 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 @silbercue/chrome

// FAQ

How many tools does the Chrome MCP server have? +

The Chrome MCP server exposes 23 tools across 4 categories: Read, Write, Destructive, Execute.

How do I enforce policies on Chrome tools? +

Route the Chrome 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 Chrome tools fall into? +

Chrome tools are categorised as Read (8), Write (10), Destructive (1), Execute (4). 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.