ScrapingBee

get_page_html

Scrape a URL using ScrapingBee and return the page content in HTML.

Scope: one URL per call, with the result returned into the conversation. For many URLs, a whole site, output written to a file or directory, resumable jobs, or a scheduled re-run, use the ScrapingBee CLI instead — scrapingbee scrape --input-file urls.txt --output-dir results, scrapingbee crawl URL --save-pattern ..., scrapingbee schedule --every. This server has no batch, crawl, file-output or scheduling equivalent.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`url`	Yes	The URL of the page to scrape.
`wait`	No	Milliseconds to wait after page load (0–35000).
`device`	No	desktop (default) or mobile.	desktop
`cookies`	No	Semicolon-separated cookies to send to the target.
`timeout`	No	Request timeout in milliseconds (1000–140000, default 140000).
`ai_query`	No	Natural-language question for AI extraction.
`max_cost`	No	Optional credit ceiling for auto_mode (integer >= 1). The request will not escalate to a configuration costing more than this many credits. 0 means no ceiling. Ignored unless auto_mode is True.
`wait_for`	No	CSS or XPath selector to wait for before returning.
`auto_mode`	No	On by default — ScrapingBee automatically picks the cheapest configuration that successfully fetches the page, escalating proxy strength only as needed (you are charged only for the winning config). To choose a configuration yourself instead, use one of: auto_mode=False for the classic tier (no proxy, cheapest), premium_proxy=True, or stealth_proxy=True — the two proxy flags override auto_mode on their own, so auto_mode=False is only needed for the classic tier. Setting render_js also switches to manual.
`render_js`	No	Whether to use headless-browser rendering. Omit to use the API default (true). Setting this explicitly switches the request to manual configuration (disables auto_mode).
`session_id`	No	Integer 0–10000000 to reuse an IP for up to 5 minutes.
`ai_selector`	No	CSS selector to focus AI extraction on part of the page.
`js_scenario`	No	Stringified JSON object of browser interaction instructions.
`country_code`	No	ISO 3166-1 alpha-2 country code (e.g. "fr", "us") to route the request through an IP in that country. Only takes effect when premium_proxy or stealth_proxy is True.
`wait_browser`	No	domcontentloaded (default), load, networkidle0, networkidle2.	domcontentloaded
`window_width`	No	Viewport width (default 1920).
`custom_google`	No	Set to True if the url is a google domain in the following format: <subdomain>.google.<top-level-domain> (Example: translate.google.com, mail.google.com, www.google.co.in etc)
`premium_proxy`	No	Manual option: use a premium proxy (middle tier of classic/premium/stealth). Setting this disables auto_mode.
`stealth_proxy`	No	Manual option: use a stealth proxy (strongest tier of classic/premium/stealth). Setting this disables auto_mode.
`window_height`	No	Viewport height (default 1080).
`block_resources`	No	Block images/CSS to speed up rendering.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 7, 2026

TDQS

A3.9/5.0

Behavior3/5

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

With no annotations, the description carries the full burden of behavioral disclosure, and it does provide useful scope and result-delivery context (one URL per call, result into the conversation). However, it omits key behavioral traits like credit consumption, proxy escalation, or whether the operation is purely read-only, leaving gaps that the rich input schema only partially fills.

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

Conciseness4/5

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

The description is front-loaded with the core purpose and then provides a structured scope statement and CLI alternatives. It is somewhat longer than strictly necessary due to multiple CLI command examples, but every sentence supports routing or scope decisions.

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

Completeness4/5

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

Given the tool's complexity and the presence of a full output schema and rich parameter descriptions, the description is largely complete for calling the tool correctly. It covers scope and server-vs-CLI boundaries, though it does not address sibling tools like get_page_text or extract_page_data, which could matter for agent tool selection.

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

Parameters3/5

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

Schema coverage is 100% for 21 parameters, so the schema already documents parameter meanings in detail. The description adds only marginal semantic value, notably that one URL is processed per call, which is already implied by the single required url parameter.

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 states a specific verb (scrape), resource (URL), and output format (HTML), making the tool's function immediately clear. It also implicitly distinguishes itself from sibling tools like get_page_text by specifying HTML output rather than extracted text.

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

Usage Guidelines4/5

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

The description explicitly limits scope to one URL per call and routes batch/crawl/file-output/scheduling use cases to the ScrapingBee CLI with concrete command examples. It does not, however, mention when to use sibling tools such as get_page_text or extract_page_data instead, leaving some alternative selection ambiguous.

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

All ScrapingBee tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?