Skip to main content
Glama

ScrapingAnt (Unofficial)

Scrapingant Scrape

scrapingant_scrape
Read-onlyIdempotent

Scrape a web page and return its raw HTML via ScrapingAnt (headless-browser rendering + rotating proxies). Handles JS-heavy sites and anti-bot pages. Example: scrapingant_scrape({ url: "https://example.com", browser: true, _apiKey: "your-key" })

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "url": "https://example.com/products",
      "_apiKey": "your-scrapingant-api-key",
      "browser": true
    },
    "name": "scrapingant_scrape"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesThe absolute URL of the page to scrape, e.g. "https://example.com/products"
_apiKeyYesYour ScrapingAnt API key. Sign up free at https://app.scrapingant.com/signup
browserNoRender the page in a headless browser (executes JavaScript). Default true. Set false for a faster raw HTTP fetch of static pages.
js_snippetNoCustom JavaScript to run in the page after load (plain JS, this pack base64-encodes it for you). Only applies when browser rendering is on.
proxy_typeNoProxy pool to use: "datacenter" (default, cheaper) or "residential" (harder to block).
proxy_countryNoTwo-letter ISO country code for the proxy exit location, e.g. "US", "GB", "DE".
wait_for_selectorNoCSS selector to wait for before returning (e.g. ".price"). Only applies when browser rendering is on.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / js_snippet / description
      Previous value: -"Custom JavaScript to run in the page after load (plain JS — this pack base64-encodes it for you). Only applies when browser rendering is on."New value: +"Custom JavaScript to run in the page after load (plain JS, this pack base64-encodes it for you). Only applies when browser rendering is on."
  2. First observed

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already declare readOnly/openWorld/idempotent/non-destructive, so the safety profile is covered. The description adds real value on mechanics (proxy rotation, anti-bot handling, browser rendering toggle) but says nothing about credit consumption, rate limits, failure modes (blocked page, timeout), or what happens on error.

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 the core action and return type, then mechanism, then a compact call example. The example partly duplicates the schema's own examples array, which is the only wasted space; otherwise no 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?

Seven parameters are all schema-documented, annotations carry safety semantics, and the description states the return value (raw HTML), so no output schema is needed. Gaps are operational rather than structural: cost/credits and error behavior are unaddressed for a proxy-billed scraping tool.

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 every parameter including js_snippet, proxy_type, proxy_country and wait_for_selector is already documented. The description's inline example echoes a subset of params rather than adding synthesis or defaults beyond the schema.

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?

Specific verb and resource ("Scrape a web page and return its raw HTML") plus the mechanism (headless-browser rendering + rotating proxies) and target site class (JS-heavy, anti-bot). "Raw HTML" implicitly distinguishes it from the markdown/extract siblings, but neither sibling is named, so an agent must infer the split.

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?

"Handles JS-heavy sites and anti-bot pages" implies the use case and the browser=true default is a hint about the fast path, but there is no explicit when-not guidance and no named alternative such as scrapingant_markdown or scrapingant_extract for agents who want markdown or structured extraction.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.