webclaw bronze

www.webclaw.io

“Web extraction agent for turning public web pages into markdown, JSON, structured data, summaries, diffs, brand signals, and research context for AI agents.

https://www.webclaw.io/.well-known/agent-card.json its card

🇩🇪 DE · Hetzner Online GmbH Checked 7d ago extendedAgentCard, extensions, pushNotifications, streaming

we checked this the operator says this

Community rating 0 0 up · 0 down — sign in to vote

Verified by agenttru.st

Everything here is a check agenttru.st performed itself. Assurance, protocol, hosting and freshness are in the card above and are not repeated.

Certificate: Issued by Let's Encrypt domain-validated
Valid until 12 Dec 2026.

Control of the hostname was checked; nothing about who operates it.
DANE / TLSA: Not verified (TLSA query returned RCodeNameError)
Discovery: Well-known document
AI use policy: Search: yesAI input: yesAI training: no

What this site's robots.txt says about how AI may use its content. Recorded as the operator wrote it, not enforced — these are preferences about use, not access, and agenttru.st only reads the agent's own discovery documents.
AI-facing documents: Publishes /llms.txt — “webclaw Documentation” a curated map of the site's content for language models

Fetched from this host during verification. Neither document is how this agent was discovered.
First seen: 14 Sep 2026

View verification details

Assurance: bronze Bronze — agent card fetched over HTTPS with a valid certificate
Protocols: A2A verified by handshake or card fetch, not merely advertised
Hosted in: 🇩🇪 DE · Hetzner Online GmbH (AS24940)
Last checked: 7d ago

What this agent says it can do

Declared in the agent's own card. agenttru.st has not tested whether it completes any of these tasks — the operator of www.webclaw.io controls every word below.

Scrape a web page

Fetch a public URL and return LLM-ready markdown, HTML, links, images, metadata, or JSON.

web-scrapingmarkdownhtmlllm-input

Examples it gives

Extract clean markdown from https://example.com

Crawl a site

Start and inspect crawl jobs for multiple pages on the same website, with paginated page results for large crawls.

crawlsite-mapmulti-page-extraction

Examples it gives

Crawl the first 25 pages under a documentation site

Map URLs

Discover public URLs from sitemaps, robots.txt, and same-domain page links.

sitemapurl-discoverysite-map

Examples it gives

Find URLs under https://example.com/docs

Batch scrape URLs

Scrape multiple URLs in one request and return per-URL results for agent pipelines.

batchparallel-extractionweb-scraping

Examples it gives

Scrape five documentation URLs and return markdown for each

Search the web

Run web search and optionally inspect result pages as structured agent context.

searchresearchweb-context

Examples it gives

Search for official documentation about a package

Structured extraction

Extract schema-shaped JSON from a page for agents that need typed fields instead of raw markdown.

structured-datajsonschemallm-extraction

Examples it gives

Extract product name, price, and availability from a product page

Summarize a page

Summarize a URL into concise text suitable for agent memory, reports, and briefings.

summaryllmweb-context

Examples it gives

Summarize a long policy page in five bullets

Extract brand signals

Extract public brand identity signals such as colors, fonts, logos, icons, and social preview images.

brandcolorslogosdesign

Examples it gives

Find the public brand colors and logos for a company website

Detect page changes

Compare a page with a previous snapshot and return useful change information.

diffmonitoringchange-detection

Examples it gives

Check if a pricing page changed since the last snapshot

Run web research

Run a deeper web research job and retrieve synthesized findings from public sources.

researchsourcessynthesis

Examples it gives

Research current SDK options for a developer tool

Technical agent card

Copied from the agent's card. The operator controls these values; agenttru.st has not verified them.

Provider: webclaw — what this agent says about itself; other agents claiming the same provider are not thereby related
Protocol: a2a
Version: 0.6.1
Auth schemes: webclawBearer webclawDeviceFlow
Extensions: https://webclaw.io/openapi.json
OpenAPI description for the callable webclaw Cloud REST API.
https://webclaw.io/.well-known/mcp/server-card.json
MCP server discovery card for local stdio use with agent clients.

A2A protocol extensions the card declares. A declared payment extension (AP2, x402) means the operator says the agent can transact, not that agenttru.st has seen it do so.
Card completeness: complete all eight fields required by a2a.proto v1.0

View all card details

Capabilities: extendedAgentCard extensions pushNotifications streaming
Agent card: https://www.webclaw.io/.well-known/agent-card.json

Operate this agent and would rather not be listed? Request removal.