Bastion Helix Agent Lens

com.bastionhelix/agent-lensbastionhelix.comstreamable-httpv1.0.0Scanned 2 hours ago

Web pages for AI agents: may-I-use checks, prompt-injection flags, Markdown, JSON, screenshots

8 tools: 5 change things and 3 only read.

Reads private data · 0
Reads text others write · 7
Can send data out · 7
No findings

Anlyon alternative

5 of these tools change something. Run those as governed actions.

Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.

Anlyon does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.

Import an OpenAPI spec →

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

8 tools

Changes things 5Creates or changes something that can be changed back.Claude Code: ask

creditsFree.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it
Free. Credits remaining on the API key sent in the Authorization header (1 credit = US$0.001).
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
deltaFor pages an agent checks again and again.Reads text others writeCan send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it
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).
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
extractNo AI model involved: returns the structured data the page already publishes — JSON-LD / schema.org objects (products, articles, events, organisations, breadcrumbs), prices and off…Reads text others writeCan send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it
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).
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
preflightFree.Reads text others writeCan send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it
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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
siteFree.Reads text others writeCan send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it
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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true

Only reads 3Looks things up and changes nothing.Show 3 read-only tools

actionsReturns 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.Reads text others writeCan send data outNo findings
Why it is in this group
- The description's first verb is "return": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it
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).
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
readReturns the main content of a web page as clean Markdown with absolute links.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "read" says "read": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe description's first sentence says "return" and "web": it reads web pages, which anyone can write.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it
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).
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
screenshotPNG screenshot of a page at 1280×800 (or the full page).Reads text others writeCan send data outNo findings
Why it is in this group
- The name "screenshot" says "screenshot": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it
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).
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data.

Reads private data0: Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write7: Brings in text someone else can write: web pages, inbound email, messages, issues and comments.; actions
delta
extract
preflight
read
screenshot
site
Can send data out7: Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.; actions
delta
extract
preflight
read
screenshot
site

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

Changes to its tool definitions and to its remote endpoint, newest first.

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

All changes to this server

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http agent-lens https://lens.bastionhelix.com/mcp

claude mcp add --transport http agent-lens https://lens.bastionhelix.com/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json

{
  "permissions": {
    "allow": [],
    "ask": [
      "mcp__agent-lens__preflight",
      "mcp__agent-lens__read",
      "mcp__agent-lens__actions",
      "mcp__agent-lens__extract",
      "mcp__agent-lens__delta",
      "mcp__agent-lens__site",
      "mcp__agent-lens__screenshot",
      "mcp__agent-lens__credits"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as agent-lens. Review it before you use it.

Capability tags behind 7 rules

mcp__agent-lens__preflight untrusted-input, outbound
mcp__agent-lens__read untrusted-input, outbound
mcp__agent-lens__actions untrusted-input, outbound
mcp__agent-lens__extract untrusted-input, outbound
mcp__agent-lens__delta untrusted-input, outbound
mcp__agent-lens__site untrusted-input, outbound
mcp__agent-lens__screenshot untrusted-input, outbound

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://anlyon.dev/api/v1/servers/com.bastionhelix/agent-lens/verify?hash=09580c5dcf6e799a4261c210480f7f83f870c3977d5e29b3ca5438ce0e5687dd" | jq -e '.changed == false'

Pinned hash 09580c5dcf6e, from Oct 29, 2026, 03:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://anlyon.dev/servers/com.bastionhelix/agent-lens/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

[![anlyon.dev](https://anlyon.dev/badge/com.bastionhelix/agent-lens.svg)](https://anlyon.dev/servers/com.bastionhelix/agent-lens)

Source: MCP Registry. Synced Oct 29, 2026, 03:17 UTC.