Skip to main content
Glama
zoharbabin

Google Researcher MCP

Scrape Page (+ YouTube, PDF, DOCX, PPTX)

scrape_page
Read-only

Extract text content from web pages, YouTube videos, and documents (PDF, DOCX, PPTX) with support for JavaScript-rendered pages.

Instructions

Extract text content from a URL. Automatically handles: web pages (static + JavaScript-rendered), YouTube videos (extracts transcript), and documents (PDF, DOCX, PPTX).

When to use:

  • You already have a specific URL to extract content from

  • Need content from YouTube videos, PDFs, or Office documents

  • Want to check page structure before fetching full content (preview mode)

When to use search_and_scrape instead:

  • Researching a topic across multiple sources

Content size control:

  • max_length: Limit response size (default: server max of 50KB)

  • mode: 'full' returns content, 'preview' returns metadata + structure only

Preview mode benefits:

  • Check content size before fetching full content

  • Get page structure (headings) to decide which sections to read

  • Avoid context exhaustion with very large pages

Caching: Results cached for 1 hour.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlYesThe URL to scrape. Supports: web pages (static HTML and JavaScript-rendered SPAs), YouTube videos (extracts transcript automatically), and documents (PDF, DOCX, PPTX - extracts text content).
max_lengthNoMaximum content length in characters. Content exceeding this will be truncated at natural breakpoints. Default: server max (50KB).
modeNo'full' returns content (default), 'preview' returns metadata and structure without full content.full

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlYesThe URL that was scraped
contentYesThe extracted text content from the page
contentTypeYesThe type of content that was extracted
contentLengthYesLength of the extracted content in characters
truncatedYesWhether the content was truncated due to size limits
estimatedTokensYesEstimated token count (~4 chars/token)
sizeCategoryYesSize category based on content length
originalLengthNoOriginal content length before truncation
metadataNoAdditional metadata for documents
citationNoCitation information with metadata and formatted strings
previewNoContent preview with structure (when mode=preview)
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations indicate readOnlyHint=true and openWorldHint=true, and the description adds value by explaining automated handling of JavaScript-rendered pages, YouTube transcripts, document extraction, caching (1 hour), and truncation at natural breakpoints. No contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with sections, bullet points, and clear headings. It is informative yet concise, with every sentence adding unique value. No fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has an output schema and full parameter coverage, the description covers all relevant aspects: supported formats, content control, preview mode, caching, and alternatives. It feels complete for agent decision-making.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with good descriptions for all parameters. The description adds extra context like default max_length (50KB server max) and preview mode benefits, which enhances understanding beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Extract text content from a URL' and then enumerates supported types (web pages, YouTube, PDF, DOCX, PPTX). The title also lists these formats, making the purpose distinct from siblings like search_and_scrape.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description includes explicit 'When to use:' and 'When to use search_and_scrape instead:' sections, guiding the agent on tool selection. It also details content size control and preview mode benefits, offering clear usage context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/zoharbabin/google-researcher-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server