Skip to main content
Glama
Sign In

Scrapling x402 Data Store

by io.github.bnth09productions-maker
OverviewDiscussionsAdmin

Scrape a URL (paid)

scrape_url
Read-only

PAID, $0.001-$0.025 USDC. Any web page as clean, LLM-ready Markdown (boilerplate stripped) for your agent's context, e.g. url=https://example.com. Fetches the URL live (typically 1-5 s; stealth tier longer) and returns clean Markdown, JSON-LD, HTML tables and links as JSON. Tiers: cached_intel $0.001 (recent cached copy), static_scrape $0.005 (live fetch, default for normal pages), stealth_browser $0.025 (headless browser for JavaScript or Cloudflare-protected pages). An unpaid call returns the exact x402 price.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "url": "<url>"
    },
    "name": "scrape_url"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesPage to scrape.
tierNoauto
api_keyNoOptional prepaid key (sk_scrapling_...) or catalog pass token (sdp_..., from pass_day/pass_month). Otherwise pay per call with x402 via _meta['x402/payment'].
css_selectorNoOptional CSS selector to scope extraction.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / api_key / description
      Previous value: -"Optional prepaid key (sk_scrapling_...). Otherwise pay per call with x402 via _meta['x402/payment']."New value: +"Optional prepaid key (sk_scrapling_...) or catalog pass token (sdp_..., from pass_day/pass_month). Otherwise pay per call with x402 via _meta['x402/payment']."
  2. First observed

TDQS

A4.2/5.0
Behavior5/5

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

Goes well beyond the readOnly/openWorld annotations: discloses per-call cost range, per-tier pricing, typical latency (1-5 s, longer on stealth), boilerplate stripping, payment via x402 or api_key, and that an unpaid call returns the exact x402 price. That is precisely the operational context an agent needs before spending money.

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-loads the critical fact (PAID, price range) in the first clause, then what it returns, then tier costs, then payment failure behavior. Dense but every sentence carries information; slight compression cost in the run-on tier sentence.

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?

With no output schema, the description carries the return-value burden and does so by enumerating Markdown, JSON-LD, tables and links as JSON. Payment, latency, tiering and unpaid-call behavior are covered; rate limits and error modes beyond payment are omitted.

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

Parameters4/5

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

Schema coverage is 75%, and the biggest gap, the tier enum with no schema description, is fully remedied: each tier value is explained with cost and use case. The url example and tier defaulting are clarified; api_key and css_selector are left to the schema, which documents them adequately.

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 and resource ('Fetches the URL live ... returns clean Markdown, JSON-LD, HTML tables and links as JSON') and specifies the output shape. It does not name or differentiate itself from the closest sibling, scrape_text, so an agent must infer the split between the two Scrape tools.

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?

Gives explicit selection guidance for tiers: cached_intel for recent cached copies, static_scrape as the default for normal pages, stealth_browser for JavaScript or Cloudflare-protected pages. It misses the cross-tool decision (when to use scrape_text instead) and any 'do not use' conditions.

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

All Scrapling x402 Data Store toolsInspect
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