Skip to main content
Glama

Scrape

scrape
Read-only

Extract content from any URL as Markdown or HTML. Returns the page's content in the chosen format (Markdown by default) with its title, description and links. Use when you have a URL and need what the page says. Start with fast; use standard for pages that need JavaScript and thorough only for sites that block scrapers. To pull specific fields into JSON use documents; to see the page as an image use screenshot. Cost: fast 1 credit, standard 2 credits, thorough 5 credits, charged only when a call succeeds.

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"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesURL to scrape.
modeNoMode: fast (Raw HTTP, no JS. <1s), standard (Full JS rendering. 2-5s), thorough (Anti-bot proxies + JS rendering, waits for late scripts. 15-35s).
outputNoContent format.markdown
timeoutNoSeconds the page may take to load (up to 55).
wait_forNoCSS selector to wait for (standard and thorough modes).
main_content_onlyNoLeave out the page's menus, header and footer (default true). Set false to keep them, such as a site-wide notice or the footer's contact details.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / main_content_only
      Added value: +{
      +  "default": true,
      +  "description": "Leave out the page's menus, header and footer (default true). Set false to keep them, such as a site-wide notice or the footer's contact details.",
      +  "type": "boolean"
      +}
    • changedInput schema / properties / mode / description
      Previous value: -"Mode: fast (Raw HTTP, no JS. <1s), standard (Full JS rendering. 2-5s), thorough (Anti-bot proxies + JS rendering. 10-30s)."New value: +"Mode: fast (Raw HTTP, no JS. <1s), standard (Full JS rendering. 2-5s), thorough (Anti-bot proxies + JS rendering, waits for late scripts. 15-35s)."
  2. First observed

TDQS

A4.9/5.0
Behavior5/5

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

Annotations already cover the read-only/open-world/no-destruction profile, and the description adds material context beyond them: the shape of the return payload (content plus title, description and links), per-mode credit prices, and the fact that credits are charged only on success. That billing and return-shape disclosure is exactly what an agent needs before picking an expensive mode.

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?

Five short sentences, front-loaded with purpose then guidance then cost; no filler and nothing repeated from the schema verbatim.

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?

No output schema exists, yet the description still tells the agent what comes back (content in the chosen format with title, description and links), and it covers cost, timing expectations and sibling routing. Nothing needed to call or choose this tool is missing.

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?

With 100% schema coverage the baseline is 3, and the description earns above that by explaining the tradeoff logic behind mode selection and tying it to cost, though it says nothing extra about main_content_only, wait_for, or timeout beyond what the schema already documents.

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?

Opens with a specific verb and resource ("Extract content from any URL as Markdown or HTML") and immediately distinguishes itself from siblings by naming documents and screenshot as the tools for JSON field extraction and imaging respectively.

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?

Gives an explicit trigger ("Use when you have a URL and need what the page says"), an escalation ladder across modes (fast first, standard for JS, thorough only for scraper-blocking sites), and two named alternatives with the conditions that select them.

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.