Skip to main content
Glama

diogenes-web-scraping-engine-mcp

OpenGraph, Twitter Cards & JSON-LD Microdata Extractor

extract_structured_metadata
Read-onlyIdempotent

Extracts OpenGraph tags, Twitter Card metadata, canonical URLs, and Schema.org JSON-LD microdata scripts from live URLs or raw HTML. Accepts either 'url' to fetch directly or raw 'html_content' from upstream scrape_readable_article; for extracting contact emails and phone numbers, use extract_contact_info instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'url' or 'html_content' ('metadata_targets' defaults to 'all_protocols'), supports '?demo=true' or L402 (10 sats), and returns HTTP 400 if invalid.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "extract_structured_metadata"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlNoOptional web page URL to fetch and parse directly, bypassing an out-of-band fetch step.
html_contentNoSource HTML string containing head tags, OpenGraph meta properties, or JSON-LD scripts.
include_faviconsNoWhether to extract favicon links and Apple Touch icon references.
metadata_targetsNoTarget metadata protocol filter: all protocols, OpenGraph and Twitter, or Schema.org JSON-LD.

Output Schema

NameRequiredDescriptionDefault
open_graphYesStructured OpenGraph properties including og:title, og:image, and og:description.
twitter_cardYesTwitter Card metadata including twitter:card, twitter:creator, and twitter:image.
canonical_urlYesCanonical canonical link target or empty string if unspecified.
json_ld_schemasYesParsed Schema.org JSON-LD structured data objects.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / url
      Added value: +{
      +  "description": "Optional web page URL to fetch and parse directly, bypassing an out-of-band fetch step.",
      +  "type": "string"
      +}
    • removedInput schema / required
      Removed value: -[
      -  "html_content"
      -]
  2. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Beyond the annotations (readOnly, idempotent, non-destructive), it discloses statelessness, a 32 KB payload cap, 60 RPM throttling, a 10 s timeout, an L402 payment path (10 sats) and ?demo=true, plus HTTP 400 on invalid input. These are real operational constraints the annotations do not carry. Minor caveat: 'fetch from live URLs' sits somewhat oddly against openWorldHint=false, so a note on outbound-fetch behavior would sharpen it, but nothing here contradicts the read-only profile.

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-loaded with purpose, then routing guidance, then constraints, so the important information comes first. The third sentence is dense with parentheticals (size limit, RPM, payment, demo flag, error code) and could be split for scanability, but every clause carries operational information.

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?

For a 4-parameter stateless extractor with an output schema and full annotation coverage, the definition supplies everything an agent needs: input routes, protocol filter default, size and rate limits, payment/demo behavior, and failure signaling. Return-value shape is correctly left to the output schema.

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 100%, so the baseline is 3; the description adds value by stating that 'url' and 'html_content' are alternative input routes and that 'metadata_targets' defaults to 'all_protocols', a default the schema does not declare. It does not clarify mutual exclusivity of url/html_content or the effect of include_favicons.

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 opens with a specific verb and enumerates the exact resources extracted (OpenGraph tags, Twitter Cards, canonical URLs, Schema.org JSON-LD), which matches the title. It also names the sibling it is not (extract_contact_info), so an agent can distinguish it from extract_clean_markdown or scrape_readable_article without opening any schema.

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?

It states both input routes explicitly ('url' to fetch directly vs raw 'html_content' from upstream scrape_readable_article) and gives an exclusion rule: use extract_contact_info for contact emails and phone numbers. That is explicit when-to-use, when-not, and the alternative.

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.

Resources