get_document

Retrieve the DOM document structure with configurable depth and shadow DOM access. Fetches the document tree starting from the root element, with control over traversal depth and shadow DOM boundary crossing. This provides the foundation for all DOM inspection operations by establishing the docum...

SERVERChrome Devtools SOURCEbenjaminr/chrome-devtools-mcp
Low RISK CLASS
Category Read
Parameters 00 required
Recommended Allowedsee the rule below
Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/benjaminr-chrome-devtools-mcp/get-document.md

What get_document does on Chrome Devtools

AI agents call get_document to retrieve information from Chrome Devtools without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Why get_document is rated Low

This tool retrieves and reads DOM structure information without side effects. While it operates within a browser context (Chrome DevTools), it only fetches and returns data about the page structure. It does not execute code, modify content, delete anything, or trigger external operations.

From the tool's definition The tool 'Retrieve the DOM document structure' with 'configurable depth and shadow DOM access' performs inspection and retrieval operations only.

Risk signalsBulk/mass operation — affects multiple targets · Admin/system-level operation

Questions about get_document

What does the get_document tool do? +

Retrieve the DOM document structure with configurable depth and shadow DOM access. Fetches the document tree starting from the root element, with control over traversal depth and shadow DOM boundary crossing. This provides the foundation for all DOM inspection operations by establishing the document structure. The depth parameter controls how deep into the DOM tree to traverse, while the pierce option enables inspection of shadow DOM content that would normally be encapsulated. Args: depth: Maximum depth to retrieve from document root (default: 1). Use -1 to retrieve the entire document tree. Higher depths provide more complete structure but increase response size. pierce: Whether to traverse shadow DOM boundaries (default: False). When True, includes shadow DOM content in the tree structure. Returns: Document structure dictionary containing: - success: Boolean indicating retrieval success - message: Summary of document structure retrieved - data: Complete DOM tree structure from the document root, including all child elements up to the specified depth Note: Large documents with high depth settings may produce substantial responses. Consider using moderate depths for initial exploration, then targeting specific areas for detailed analysis. It is categorised as a Read tool in the Chrome Devtools MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on get_document? +

Register the Chrome Devtools MCP server in PolicyLayer and add a rule for get_document: 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 Chrome Devtools. Nothing to install.

What risk level is get_document? +

get_document is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit get_document? +

Yes. Add a rate_limit block to the get_document 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 get_document completely? +

Set action: deny in the PolicyLayer policy for get_document. 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 get_document? +

get_document is provided by the Chrome Devtools MCP server (benjaminr/chrome-devtools-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

More on Chrome Devtools, and thousands of servers like it.

// THE MCP REGISTRY

PolicyLayer tracks 44,603 MCP servers and 515,000+ tools.

Every server has a live record: who publishes it, whether it answers without auth, its risk grade, every tool classified, the recommended policy. This page is one line of Chrome Devtools's. Pull the full record:

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.