MCP Server Steel Scraper

visit_with_browser

Visit any website with browser automation to extract clean page content as Markdown, HTML, Readability, or cleaned HTML, plus screenshots and PDFs; handles JavaScript.

Instructions

Visit any website using full browser automation (stealth mode, anti-detection). Returns page content in your chosen format: 'html' for raw HTML source, 'markdown' for clean formatted text (recommended for reading), 'readability' for Mozilla Readability format, or 'cleaned_html' for cleaned HTML. Supports screenshot and PDF generation. Automatically handles JavaScript rendering and provides clean output by default.

Input Schema

TableJSON Schema

Name	Required	Description
`pdf`	No	Generate a PDF of the page (returns base64 encoded PDF)
`url`	Yes	The complete URL to scrape (must include http:// or https://)
`delay`	No	Delay in seconds to wait after page load before scraping
`format`	No	Content formats to extract: 'html'=raw HTML source (may be very large), 'markdown'=clean formatted text converted from HTML (recommended for reading), 'readability'=Mozilla Readability format, 'cleaned_html'=cleaned HTML. You can request multiple formats.
`logUrl`	No	URL to send logs to for debugging purposes
`proxyUrl`	No	Proxy URL to use for the request (e.g., 'http://proxy:port')
`maxLength`	No	Maximum characters to return (optional). Smart defaults: markdown=8000, readability=10000, html=15000, cleaned_html=12000. For markdown, automatically reserves space for metadata.
`screenshot`	No	Take a screenshot of the page (returns base64 encoded image)
`verboseMode`	No	Return full metadata instead of clean content-focused output (optional, default: false). Use when you need detailed scraping information.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.0.3Sep 13, 2026

TDQS

A3.7/5.0

Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses stealth mode/anti-detection, automatic JavaScript rendering, and clean output by default, and notes screenshot/PDF return base64. It omits failure behavior, timeouts, and any rate-limiting or auth constraints.

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?

Front-loaded with purpose, then capabilities, then return formats in three compact sentences. Minor redundancy in re-listing formats that the schema enum already enumerates, but no wasted filler.

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?

Nine parameters and no output schema, yet the description covers the primary capability set, default output behavior, and the shape of non-text returns (base64). Error/edge-case behavior is the only notable gap; overall complete enough to call correctly.

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 description coverage is 100%, so the schema already documents every parameter including format meanings and maxLength smart defaults. The description largely mirrors that (format enum meanings) rather than adding semantics beyond it, so the baseline 3 applies.

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

Purpose4/5

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

States a specific verb+resource: 'Visit any website using full browser automation' and enumerates the output formats. Very clear what the tool does, though with no sibling tools there is nothing to differentiate against, capping it below the top mark.

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

Usage Guidelines3/5

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

Usage guidance is embedded in parameter advice ('recommended for reading' for markdown, 'Use when you need detailed scraping information' for verboseMode) but there is no explicit when-to-use/when-not framing for the tool overall, and no alternatives exist to route to.

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

Deploy Server

Other Tools

visit_with_browserA