Skip to main content
Glama
us

crw-mcp

by us
OverviewSchemaRelated ServersScoreDiscussions
Rust
Hybrid

Scrape URL

crw_scrape
Read-onlyIdempotent

Scrape any URL to clean markdown, HTML, links, or images. Control extracted content with CSS selectors, JS rendering, and main-content filtering for AI-ready data.

Instructions

Scrape one URL to markdown, HTML, or links.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlYesURL to scrape
formatsNoOutput formats (default ["markdown"])
waitForNoMs to wait after JS render for late content
renderJsNoForce JS render (true), HTTP-only (false), omit = auto
rendererNoPin renderer; non-auto hard-pins and implies renderJs:true (default auto). 'camoufox' requires the server's opt-in camoufox tier to be configured.
maxLengthNoMax chars per content field; 0 = unbounded (default ~15000)
excludeTagsNoCSS selectors to exclude
includeTagsNoCSS selectors to include
onlyMainContentNoStrip nav/footer; main content only (default true)

Schema Changelog

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

  1. Changed1 schema field changedv0.30.0
    • changedInput schema / properties / formats / items / enum
      Previous value: -[
-  "markdown",
-  "html",
-  "links"
-]New value: +[
+  "markdown",
+  "html",
+  "links",
+  "images"
+]
  2. Changed2 schema fields changedv0.18.0
    • changedInput schema / properties / renderer / description
      Previous value: -"Pin renderer; non-auto hard-pins and implies renderJs:true (default auto)"New value: +"Pin renderer; non-auto hard-pins and implies renderJs:true (default auto). 'camoufox' requires the server's opt-in camoufox tier to be configured."
    • changedInput schema / properties / renderer / enum
      Previous value: -[
-  "auto",
-  "lightpanda",
-  "chrome",
-  "playwright"
-]New value: +[
+  "auto",
+  "lightpanda",
+  "chrome",
+  "playwright",
+  "camoufox"
+]
  3. Changed9 schema fields changedv0.16.0
    • changedInput schema / properties / excludeTags / description
      Previous value: -"CSS selectors to exclude from output"New value: +"CSS selectors to exclude"
    • changedInput schema / properties / formats / description
      Previous value: -"Output formats (default: [\"markdown\"])"New value: +"Output formats (default [\"markdown\"])"
    • changedInput schema / properties / includeTags / description
      Previous value: -"CSS selectors to include (only content matching these selectors)"New value: +"CSS selectors to include"
    • addedInput schema / properties / maxLength
      Added value: +{
+  "description": "Max chars per content field; 0 = unbounded (default ~15000)",
+  "minimum": 0,
+  "type": "integer"
+}
    • changedInput schema / properties / onlyMainContent / description
      Previous value: -"Extract only the main content, removing nav/footer/etc (default: true)"New value: +"Strip nav/footer; main content only (default true)"
    • changedInput schema / properties / renderJs / description
      Previous value: -"Render JavaScript before extracting (true = force JS, false = HTTP only, omit = auto-detect or use the server's render_js_default)"New value: +"Force JS render (true), HTTP-only (false), omit = auto"
    • changedInput schema / properties / renderer / description
      Previous value: -"Pin this request to a specific renderer. \"auto\" (default if omitted) uses the configured fallback chain. Other values hard-pin to a single renderer with no fallback. Pinning a non-auto value implies renderJs:true unless renderJs:false is set explicitly."New value: +"Pin renderer; non-auto hard-pins and implies renderJs:true (default auto)"
    • changedInput schema / properties / url / description
      Previous value: -"The URL to scrape"New value: +"URL to scrape"
    • changedInput schema / properties / waitFor / description
      Previous value: -"Milliseconds to wait after JS rendering for late content/XHRs"New value: +"Ms to wait after JS render for late content"
  4. Addedv0.9.1
  5. Removedv0.8.3
  6. Changed3 schema fields changedv0.6.2
    • addedInput schema / properties / renderJs
      Added value: +{
+  "description": "Render JavaScript before extracting (true = force JS, false = HTTP only, omit = auto-detect or use the server's render_js_default)",
+  "type": "boolean"
+}
    • addedInput schema / properties / renderer
      Added value: +{
+  "description": "Pin this request to a specific renderer. \"auto\" (default if omitted) uses the configured fallback chain. Other values hard-pin to a single renderer with no fallback. Pinning a non-auto value implies renderJs:true unless renderJs:false is set explicitly.",
+  "enum": [
+    "auto",
+    "lightpanda",
+    "chrome",
+    "playwright"
+  ],
+  "type": "string"
+}
    • addedInput schema / properties / waitFor
      Added value: +{
+  "description": "Milliseconds to wait after JS rendering for late content/XHRs",
+  "type": "integer"
+}
  7. First observedv1.0.0

TDQS

A3.7/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the agent knows this is a safe, non-destructive operation. The description adds minimal behavioral context beyond the 'one URL' scope, but does not disclose any additional behavior such as JS rendering defaults, pagination, or output limits. It does not contradict the 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 a single 9-word sentence that is direct and front-loaded. Every word contributes to the core purpose. It is extremely concise without being verbose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (9 parameters, 4 output formats, multiple renderer options), the description is quite thin. The rich schema compensates for parameter details, but the description fails to mention the 'images' format and provides no context about renderer behavior or when to use optional parameters. For a simple scraper, it may be sufficient, but for an AI agent selecting among multiple similar tools, more context would be helpful.

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?

The input schema covers 100% of parameters with descriptions, so the baseline is 3. The description mentions markdown, HTML, and links, but omits 'images' from the formats enum, which is a minor gap. The description does not add meaning beyond the schema for the remaining parameters.

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?

The description clearly states the action (scrape), the resource (one URL), and the output formats (markdown, HTML, or links). The phrase 'one URL' distinguishes it from siblings like crw_crawl, which implies multi-page crawling. It is specific and unambiguous.

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?

The description implies this tool is for scraping a single URL, since it says 'one URL'. However, it does not explicitly mention when to prefer this over crw_crawl, crw_map, or crw_extract, nor does it list any exclusions or prerequisites. Usage is implied rather than stated.

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/us/crw'

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