Skip to main content
Glama
scrapfly

Scrapfly MCP

Scrapfly Advanced Scraping Tool

web_scrape
Read-onlyIdempotent

Extract structured data from websites by scraping URLs with customizable HTTP methods, headers, proxies, JavaScript rendering, and anti-bot protection.

Instructions

Scrape a URL with full control. Use tool scraping_instruction_enhanced before using this tool. Prefer web_get_page for quick fetch

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlYesThe target URL to scrape.
methodNoThe HTTP method to use for the request.GET
bodyNoRequest body for POST/PUT/PATCH requests.
headersNoHTTP headers to send.
countryNoThe country to use for the proxy. Supports ISO 3166-1 alpha-2 country codes.
proxy_poolNoThe proxy pool to use. Supports public_datacenter_pool and public_residential_pool, defaults: public_datacenter_poolpublic_datacenter_pool
render_jsNoEnable JavaScript rendering with a headless browser.
rendering_waitNoWait for this number of milliseconds before returning the response.
aspNoEnable Anti Scraping Protection.
cacheNoEnable caching of the response.
cache_ttlNoCache TTL in seconds when cache is true.
cache_clearNoIf true, bypass & clear cache for this URL.
retryNoIf false, disable automatic retry on transient errors.
wait_for_selectorNo(Prefer rendering_wait). Wait for this CSS selector to appear in the page when rendering JS.
langNoLanguages to use for the request (Accept-Language header). Empty for auto-detection/Proxy Location alignment
cookiesNoCookies to send with the request.
formatNoThe desired output format for the content. Supports clean_html, markdown, text, and jsonmarkdown
format_optionsNoAdditional options (only available for markdown and text formats)
jsNoJavaScript to execute on the page.
js_scenarioNoA schema for validating a sequence of browser actions (JS Scenario) for the Scrapfly API.
screenshotsNoScreenshots with target (fullpage, selector). Example: [{ 'name': 'my_screenshot', 'target': 'fullpage' }, { 'name': 'my_screenshot2', 'target': 'selector', 'css_selector': '#price' }]
screenshot_flagsNoScreenshot flags to use for the screenshot.
timeoutNoServer-side timeout in milliseconds. (Prefer rendering_wait + timeout)
extraction_promptNo(Avoid if the llm is thinking and can process the data itself). If data extraction cannot be assumed by the current llm model,AI prompt to add step of llm assisted data extraction.
extraction_modelNoThe extraction model to use for the offloaded extraction. Exclusive with extraction_template and extraction_prompt.
powYesuse scraping_instruction_enhanced tool use for instructions

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
errorsNoErrors if any
contentYesHTML/Text/JSON depending on format
screenshotsNoScreenshots if any
status_codeYes
content_typeYes
extraction_resultNoExtracted data if extraction_prompt was provided
Behavior4/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=true, and idempotentHint=true. The description adds valuable context about the 'full control' nature of this advanced scraping tool and the prerequisite relationship with another tool. While it doesn't mention rate limits or authentication needs, it provides meaningful behavioral context beyond annotations.

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 extremely concise at just 2 sentences, with zero wasted words. It's perfectly front-loaded with the core purpose, followed by crucial usage guidance. Every sentence earns its place by providing essential information.

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 comprehensive annotations (readOnlyHint, openWorldHint, idempotentHint, destructiveHint), 100% schema description coverage, and the existence of an output schema, the description provides exactly what's needed. It states the purpose, gives critical usage guidance, and doesn't need to explain parameters or return values that are already well-documented elsewhere.

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?

With 100% schema description coverage, the input schema already documents all 26 parameters thoroughly. The description doesn't add any parameter-specific information beyond what's in the schema. The baseline of 3 is appropriate when the schema does all the heavy lifting for parameter documentation.

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?

The description clearly states the tool's purpose as 'Scrape a URL with full control', which is a specific verb+resource combination. However, it doesn't explicitly differentiate from sibling tools beyond mentioning one alternative; it could more clearly distinguish from 'screenshot' and 'scraping_instruction_enhanced'.

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 provides excellent usage guidance with explicit instructions: 'Use tool scraping_instruction_enhanced before using this tool' (prerequisite) and 'Prefer web_get_page for quick fetch' (alternative for simpler cases). This gives clear when-to-use and when-not-to-use 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/scrapfly/scrapfly-mcp'

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