Chrome Devtools

47 tools. 16 can modify or destroy data without limits.

2 destructive tools with no built-in limits. Policy required.

Last updated:

16 can modify or destroy data
31 read-only
47 tools total

Community server · catalogue entry checked 11/06/2026

How to control Chrome Devtools ↓

What Chrome Devtools exposes to your agents

Read (31) Write / Execute (13) Destructive / Financial (2)
Critical Risk

The most dangerous Chrome Devtools tools

16 of Chrome Devtools's 47 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

How to control Chrome Devtools

PolicyLayer is an MCP gateway — it sits between your AI agents and Chrome Devtools, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations
{
  "clear_all_cookies": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations
{
  "set_cookie": {
    "limits": [
      {
        "counter": "set_cookie_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "collect_css_class_names": {
    "limits": [
      {
        "counter": "collect_css_class_names_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

  1. Create a free account and register Chrome Devtools — nothing to install.
  2. Add these rules — paste them, or build them visually. Tune the limits to your setup.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
ENFORCE POLICY ON CHROME DEVTOOLS →

Instant setup, no code required.

All 47 Chrome Devtools tools

READ 31 tools
Read collect_css_class_names Collect all class names from a specified stylesheet. Args: stylesheet_id: ID of the style Read describe_element Get detailed information about a DOM element. Args: node_id: Node ID of the element Read get_all_cookies Get all browser cookies. Returns: List of all cookies with details Read get_background_colors Get background colors and font information for a DOM element. Args: node_id: Node ID of t Read get_computed_styles Retrieve computed CSS styles for a DOM element. Calculates and returns all computed CSS properties fo Read get_connection_status Get the current connection status to the browser. Retrieves comprehensive information about the curre Read get_console_error_summary Get an organised summary of console errors and warnings. Returns: Categorised summary of Read get_console_logs Get browser console logs with optional filtering. Args: level: Filter by log level (log, Read get_cookies Get browser cookies with optional domain filtering. Args: domain: Filter cookies by domai Read get_document Retrieve the DOM document structure with configurable depth and shadow DOM access. Fetches the docume Read get_element_at_position Get the DOM element at a specific screen position. Args: x: X coordinate y: Y Read get_element_attributes Get all attributes of a DOM element. Args: node_id: Node ID of the element Retur Read get_element_box_model Get the box model (layout information) of a DOM element. Args: node_id: Node ID of the el Read get_element_outer_html Get the outer HTML of a DOM element. Args: node_id: Node ID of the element Retur Read get_inline_styles Get inline CSS styles for a DOM element. Args: node_id: Node ID of the element R Read get_matched_styles Get comprehensive style information including all CSS rules matching a DOM element. Args: Read get_media_queries Get all media queries parsed by the rendering engine. Returns: List of all active media q Read get_network_requests Get captured network requests with optional filtering. Args: filter_domain: Filter by dom Read get_network_response Get detailed response data for a specific network request. Args: request_id: ID of the ne Read get_page_info Get comprehensive information about the current page. Returns: Page metrics, performance Read get_performance_metrics Get detailed performance metrics and resource timing. Returns: Comprehensive performance Read get_platform_fonts Get platform font usage information for a DOM element. Args: node_id: Node ID of the elem Read get_storage_key_for_frame Get the storage key for a specific frame. Args: frame_id: Frame ID to get storage key for Read get_storage_usage_and_quota Get storage usage and quota information for an origin. Args: origin: Security origin to c Read get_stylesheet_text Get the textual content of a CSS stylesheet. Args: stylesheet_id: ID of the stylesheet Read monitor_console_live Monitor console output in real-time for a specified duration. Args: duration_seconds: How Read query_selector Execute querySelector on a DOM node. Args: node_id: Target node ID to query within Read query_selector_all Execute querySelectorAll on a DOM node. Args: node_id: Target node ID to query within Read search_elements Search for DOM elements matching a query string. Args: query: Search query (text content, Read stop_css_coverage_tracking Stop tracking CSS rule usage and get coverage results. Returns: CSS usage analysis with c Read track_cache_storage Enable or disable cache storage tracking for an origin. Args: origin: Security origin to

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

Questions about Chrome Devtools

Can an AI agent delete data through the Chrome Devtools MCP server? +

Yes. The Chrome Devtools server exposes 2 destructive tools including clear_all_cookies, clear_storage_for_origin. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Chrome Devtools? +

The Chrome Devtools server has 1 write tools including set_cookie. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Chrome Devtools.

How many tools does the Chrome Devtools MCP server expose? +

47 tools across 4 categories: Destructive, Execute, Read, Write. 31 are read-only. 16 can modify, create, or delete data.

How do I enforce a policy on Chrome Devtools? +

Register the Chrome Devtools MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Chrome Devtools tool call.

Deterministic rules across all 47 Chrome Devtools tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Instant setup, no code required.

47 Chrome Devtools tools catalogued and risk-classified — across an index of 46,500+ MCP servers.

// WHERE THIS COMES FROM

These policies come from Chrome Devtools's registry record.

The record behind this page: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

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.