Skip to main content
Glama

Decodo

by io.github.pipeworx-io

Decodo Scrape

decodo_scrape
Read-onlyIdempotent

Scrape any web page through Decodo (formerly Smartproxy) rotating proxies and return its content. Handles anti-bot pages; use render_js:true for JavaScript-heavy sites (headless-browser rendering) and markdown:true for clean LLM-ready markdown instead of raw HTML. BYOK — _apiKey is your Decodo Web Scraping API "username:password" credentials. Example: decodo_scrape({ url: "https://example.com", render_js: true, _apiKey: "user:pass" })

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
geoNoProxy exit location as a location name, e.g. "United States", "Germany", "Japan". Default: randomized.
urlYesThe absolute URL of the page to scrape, e.g. "https://example.com/products"
_apiKeyYesDecodo Web Scraping API credentials as "username:password" (from the dashboard at https://dashboard.decodo.com — free plan available).
markdownNoReturn the page as clean markdown instead of raw HTML (ideal for feeding an LLM). Default false.
render_jsNoRender the page in a headless browser (executes JavaScript) before returning content. Default false (faster raw fetch of static pages).

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-decodo-api-key",
+    "url": "https://example.com/products"
+  },
+  {
+    "_apiKey": "your-decodo-api-key",
+    "geo": "United States",
+    "markdown": true,
+    "render_js": true,
+    "url": "https://news.example.com/article"
+  }
+]
  2. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already indicate readOnlyHint=true and destructiveHint=false, so the tool is non-destructive. The description adds value by disclosing that the tool 'handles anti-bot pages' and requires an API key via _apiKey, which are behavioral traits not covered by annotations. No contradiction with 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 extremely concise: three sentences covering purpose, optional parameter guidance, and an example. It is front-loaded with the main function and adds no fluff. Every sentence earns its place.

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 5 parameters, 100% schema coverage, no output schema, and multiple sibling tools, the description covers the essential usage scenarios. Return format is not detailed (no output schema), but the markdown option hints at output type. Overall, it is sufficiently complete for an agent to use effectively.

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 description coverage is 100%, so baseline is 3. The description adds meaningful context beyond the schema: for render_js, it explains 'headless-browser rendering'; for markdown, 'clean LLM-ready markdown'; for _apiKey, it clarifies the format and provides an example. These embellishments improve understanding.

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 tool's purpose: 'Scrape any web page through Decodo rotating proxies and return its content.' It specifies the action (scrape), target resource (any web page), and mechanism (rotating proxies). It stands out from sibling tools like decodo_amazon_product and decodo_google_search, which are more specialized, making the general scope evident.

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?

The description provides guidance on when to use key parameters: 'use render_js:true for JavaScript-heavy sites' and 'markdown:true for clean LLM-ready markdown'. It also includes an example invocation. While it lacks explicit 'when not to use' instructions, the context is clear enough for an agent to decide.

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

All Decodo 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

A4.2/5.0
Disambiguation4/5

Most tools have distinct purposes with detailed descriptions; however, the family of ask_pipeworx tools (beta, grounded) and deep_research could cause selection ambiguity despite clear documentation.

Naming Consistency3/5

Tool names lack a consistent pattern; they mix imperatives, descriptive nouns, and domain prefixes. While overall readable, the lack of uniformity makes it harder to predict naming conventions.

Tool Count4/5

34 tools is on the higher side but still within reasonable range given the broad scope (data queries, prediction markets, scraping, subscriptions, memory). Each tool appears purposeful, though some consolidation (e.g., ask_pipeworx variants) could reduce count.

Completeness4/5

The tool set covers a wide range of tasks from data querying to prediction market analysis and entity management. Minor gaps might exist (e.g., no direct social media data), but the overall coverage is extensive and sufficient for the platform's purpose.

Resources