Bastion Helix Agent Lens
Server Details
Web pages for AI agents: may-I-use checks, prompt-injection flags, Markdown, JSON, screenshots
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 8 tools
Each tool targets a distinct output: readable Markdown, structured metadata, interactive elements, screenshots, change detection, site-level metadata, URL preflight, and credit balance. Slight overlap between read/extract (both fetch page content) and site/preflight (both surface robots and Content Signals) is mitigated by clear descriptions.
All names are lowercase single words, consistent in casing and brevity, which makes the set easy to scan. They mix nouns and verbs and do not follow a strict verb_noun pattern, but the convention is still readable and non-conflicting.
Eight tools is well within the 3-15 range for a web-page access and extraction toolkit. Each tool covers a distinct agent need, and none feels redundant or missing from the core set.
The surface covers discovery (site, preflight), content access (read, extract, actions, screenshot), re-checking (delta), and account state (credits), matching the stated purpose. Form submission or multi-page crawling would be outside the lens scope, so no obvious gap remains.
Available Tools
8 toolsactionsList what can be clicked or filledBRead-onlyInspect
Returns the forms (with every field, its label and whether it is required), buttons and links on a page, each with a CSS selector an automation tool can use. Uses the rendered page when the HTML alone has none. Charged only on success. Price: US$0.004 per successful call (API key credits or x402).
Inputs: url (required), engine, user_agent.
creditsCredits left on your API keyARead-onlyInspect
Free. Credits remaining on the API key sent in the Authorization header (1 credit = US$0.001).
Inputs: no named parameters.
deltaWhat changed since last timeARead-onlyInspect
For pages an agent checks again and again. The first call returns the page as sections plus a fingerprint; send that fingerprint back as "previous" next time and get only the sections that changed (and the headings of removed ones), or changed:false. Uses HTTP ETag/Last-Modified when the site supports them. Nothing is stored on our side: the fingerprint lives with the agent. Saves tokens on every re-check. Charged only on success. Price: US$0.001 per successful call (API key credits or x402).
Inputs: url (required), engine, previous, user_agent.
extractGet the facts a page publishes, as JSONARead-onlyInspect
No AI model involved: returns the structured data the page already publishes — JSON-LD / schema.org objects (products, articles, events, organisations, breadcrumbs), prices and offers, meta and Open Graph tags, canonical URL, language versions, licence, RSS/Atom/JSON feeds, and HTML data tables as columns + rows. Exact values instead of guesses from text. Charged only on success. Price: US$0.002 per successful call (API key credits or x402).
Inputs: url (required), engine, user_agent.
preflightCheck a page before using itARead-onlyInspect
Free. Before an agent spends money or time on a URL: is it allowed (robots.txt for this service and, if you pass user_agent, for your own bot; Content Signals such as ai-input and ai-train; meta robots), does a bot check or sign-in stand in the way, and which engine each task needs — plain fetch, Kitesurf (Cloudflare's lightweight agent browser) or Chromium. Rate-limited per IP.
Inputs: url (required), user_agent.
readRead a page as clean MarkdownARead-onlyInspect
Returns the main content of a web page as clean Markdown with absolute links. Tries the cheapest way that works: plain fetch, then Kitesurf, then Chromium, and reports which one worked. Refuses (and charges nothing) when the site's robots.txt or Content Signals say no, or when a bot check answers instead of the page. Charged only on success. Price: US$0.004 per successful call (API key credits or x402).
Inputs: url (required), engine, max_chars, user_agent.
screenshotScreenshot a pageARead-onlyInspect
PNG screenshot of a page at 1280×800 (or the full page). engine "auto" uses Kitesurf unless the page needs video or WebGL, then Chromium. Charged only on success. Price: US$0.008 per successful call (API key credits or x402).
Inputs: url (required), engine, full_page, user_agent.
siteSite card for agentsARead-onlyInspect
Free. Everything an agent should know about a website before using it: its llms.txt (and llms-full.txt), sitemap (page count and first URLs), feeds, language versions, Content Signals, and which known AI crawlers and agents its robots.txt allows. Rate-limited per IP.
Inputs: url (required), user_agent.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Prompt-injection scanning and safe webpage fetching for AI agents reading untrusted content.
Web pages, JavaScript sites and PDFs to clean Markdown for AI agents, prompt injection removed.
Pages, crawls and URL batches as clean Markdown and JSON for AI agents, with an Evidence Record.
Web pages as Markdown, text or HTML, plus Google Maps places and reviews, for AI agents.
Related MCP Servers
- AlicenseBqualityBmaintenanceWeb scraping for AI agents: scrape, map, crawl and batch public pages into Markdown, tables and JSON, with an Evidence Record on every page. Blocked, empty and wrong pages come back as such, with the reason.397AGPL 3.0
- FlicenseNot gradedqualityCmaintenanceHeadless-browser-as-JSON for AI agents — POST a URL, get rendered HTML, structured DOM, visible text, title, links, and a screenshot from real Chromium, with memorymarket economics where the first agent to render a URL earns 90% of every cache-hit fee from other agents within a 10-minute TTL.-
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to capture rendered screenshots of web pages and read pages as Markdown, with explicit warnings when a capture looks blank rather than a silently empty image. Can connect to a hosted endpoint or a self-run instance, with SSRF guards preventing access to private and metadata addresses.AGPL 3.0
- AlicenseNot gradedqualityBmaintenanceStealth Chrome for AI agents: bot-protected sites, Turnstile, closed Shadow DOM, clean Markdown.626 npm13MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.