Skip to main content
Glama

Crawlbase

by io.github.pipeworx-io

Crawlbase Screenshot

crawlbase_screenshot
Read-onlyIdempotent

Capture a screenshot of a rendered web page via Crawlbase (headless browser + rotating proxies, anti-bot bypass). Returns a stored screenshot_url (JPEG, link expires after about one hour) plus crawl metadata. Requires your Crawlbase JavaScript token as _apiKey — screenshots always render in a real browser. Captures the full page by default; pass mode:"viewport" with width/height to constrain. Example: crawlbase_screenshot({ url: "https://example.com", _apiKey: "your-js-token" })

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlYesThe absolute URL of the page to screenshot, e.g. "https://example.com"
modeNoCapture mode: full rendered page by default; "viewport" captures only the visible area (pair with width/height).
widthNoViewport width in pixels (only applies with mode:"viewport").
heightNoViewport height in pixels (only applies with mode:"viewport").
scrollNoScroll the page before capture to trigger lazy-loaded content.
_apiKeyYesYour Crawlbase JavaScript token (screenshots require browser rendering). Free tier at https://crawlbase.com
countryNoTwo-letter ISO country code to route through, e.g. "US", "GB".
page_waitNoMilliseconds to wait after page load before capturing — gives animations/JS time to settle.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed1 schema field changed
    • addedInput schema / examples
      Added value: +[
+  {
+    "_apiKey": "your-crawlbase-token",
+    "url": "https://example.com"
+  },
+  {
+    "_apiKey": "your-crawlbase-token",
+    "height": 1080,
+    "mode": "viewport",
+    "page_wait": 2000,
+    "url": "https://example.com/product",
+    "width": 1920
+  }
+]
  2. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already indicate readOnlyHint, idempotentHint, and destructiveHint false. Description adds critical behavioral details: screenshot URL expires after about one hour, requires JavaScript token, renders in real browser, captures full page by default, and page_wait parameter for animations. 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?

Two concise sentences plus one line example. No fluff. Front-loaded with core purpose and key behavioral constraints (expiring URL, token requirement). Every sentence contributes value.

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 8 parameters and no output schema, description covers return value (screenshot_url and metadata) and major behaviors. Lacks mention of error handling or rate limits, but sufficient for typical usage. Could briefly note potential errors (e.g., invalid token) but not essential.

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

Parameters5/5

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

Schema has 100% coverage with descriptions already. Description adds meaning beyond schema: explains default behavior (full page), demonstrates viewport mode usage with width/height, and gives example calls showing typical usage patterns. This aids agent in understanding parameter combinations.

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?

Clearly states it captures a screenshot of a rendered web page via Crawlbase, with headless browser and anti-bot bypass. Distinguishes from siblings like crawlbase_scrape (scraping) and crawlbase_structured (structured data) by focusing on visual capture.

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?

Provides clear context: requires JavaScript token, captures full page by default, optional viewport mode. Includes examples. Does not explicitly say when not to use, but the purpose is well-defined enough to avoid confusion with alternatives.

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

All Crawlbase toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4/5.0
Disambiguation4/5

The toolset is largely distinct: scraping, research, prediction-market, memory, and subscription tools each have clear boundaries. The ask_pipeworx family and the six Polymarket tools are closely related variants, but their descriptions provide explicit usage guidance, so an agent can select correctly with attention.

Naming Consistency3/5

Most tools use snake_case with descriptive names, but conventions are mixed: brand-prefixed noun phrases (crawlbase_scrape, polymarket_arbitrage, pipeworx_trending) sit alongside verb_noun tools (compare_entities, validate_claim) and bare verbs (remember, subscribe). The result is readable but not predictable.

Tool Count2/5

At 34 tools, the server spans several distinct domains (web scraping, structured data research, prediction markets, memory, subscriptions, feedback), making it feel like a kitchen sink rather than a focused toolset. The count is beyond the 'heavy' threshold and would benefit from splitting into separate servers.

Completeness4/5

The research surface is thorough: routing, grounded answers, deep research, entity profiles, comparisons, claim validation, and identifier resolution cover most real-world data needs. Minor gaps exist, such as no explicit tool to fetch pipeworx:// resource URIs and no crawler management for the scraping side.

Resources