Skip to content

AgentRead MCP server

io.github.omarhassanatef/agentreadomarhassanatefstreamable-httpv0.2.0Scanned

Web pages to clean Markdown for AI agents. 5 free calls/day, then pay per call via x402 on Base.

3 tools: 3 only read.

Tools: 0 delete, 0 irreversible, 0 write, 3 read.
  • Reads private data · 0
  • Reads text others write · 3
  • Can send data out · 3
  • 3 findings

Sign-in required, no OAuth metadata. Remote posture

With Anlyon

Decide which of this server's tools your agent can use.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the AgentRead MCP server can do

The AgentRead MCP server is published by the GitHub account omarhassanatef. It has 3 tools. Every one of them only reads: going by their definitions, none of them creates, changes, sends or deletes anything.

3 tools bring in text other people can write (inspect_url, extract_url and extract_url_structured); 3 tools can send data out of your system (inspect_url, extract_url and extract_url_structured).

The fixed checks matched 3 findings (credentials-mention). Each one comes with the text it matched.

Its tools changed once since Anlyon Radar first saw them.

Last scanned Nov 9, 2026, version 0.2.0.

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.

3 tools

Only reads 3Show 3 read-only tools
  • extract_urlFetch a public web page and return its main content as clean Markdown with title, description, headings and extraction metadata.Reads text others writeCan send data out1 finding

    Why it is in this group

    • The description's first verb is "fetch": 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 name "extract_url" says "url": it reads web pages, which anyone can write.
    • untrusted-inputThe description's first sentence says "fetch" 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.

    Findings

    • Info

      The input schema at properties.url.description mentions "credentials".

      Matched text

      inputSchema.properties.url.description: "...or https:// URL. Default ports only; no credentials; no IP literals."

      What this check looks for
    Description, as the server wrote it
    Fetch a public web page and return its main content as clean Markdown with title, description, headings and extraction metadata. Removes navigation, ads, cookie banners and scripts. Does not execute JavaScript. Paid via x402 ($0.003 per successful call; the first 5 successful calls per day are free). Returns JSON (structuredContent + text) with schemaVersion, operation, requestedUrl, finalUrl, title, description, markdown, headings[{level,text}], truncated, extraction{method,statusCode,contentType,charset,redirects,bytesFetched,characters,totalCharacters,words,warnings,durationMs}.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • extract_url_structuredFetch a public web page and return structured data: page metadata (title, description, canonical URL, language, site name, byline), main content Markdown, ordered headings with lev…Reads text others writeCan send data out1 finding

    Why it is in this group

    • The description's first verb is "fetch": 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 name "extract_url_structured" says "url": it reads web pages, which anyone can write.
    • untrusted-inputThe description's first sentence says "fetch" 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.

    Findings

    • Info

      The input schema at properties.url.description mentions "credentials".

      Matched text

      inputSchema.properties.url.description: "...or https:// URL. Default ports only; no credentials; no IP literals."

      What this check looks for
    Description, as the server wrote it
    Fetch a public web page and return structured data: page metadata (title, description, canonical URL, language, site name, byline), main content Markdown, ordered headings with levels, and links (text + URL). Deterministic HTML processing, no LLM. Paid via x402 ($0.005 per successful call; the first 5 successful calls per day are free). Returns JSON with schemaVersion, operation, requestedUrl, finalUrl, metadata{title,description,canonicalUrl,language,siteName,byline,publishedTime}, markdown, headings, headingsTruncated, links[{text,url}], linksTruncated, truncated, extraction{...}.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • inspect_urlFree, lightweight check of a public URL: reachability, HTTP status, final URL after redirects, content type, page title, and whether extraction is likely to work.Reads text others writeCan send data out1 finding

    Why it is in this group

    • The name "inspect_url" says "inspect": 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 name "inspect_url" says "inspect" and "url": it reads web pages, which anyone can write.
    • untrusted-inputThe description's first sentence says "url": 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.

    Findings

    • Info

      The input schema at properties.url.description mentions "credentials".

      Matched text

      inputSchema.properties.url.description: "...or https:// URL. Default ports only; no credentials; no IP literals."

      What this check looks for
    Description, as the server wrote it
    Free, lightweight check of a public URL: reachability, HTTP status, final URL after redirects, content type, page title, and whether extraction is likely to work. Downloads at most a small prefix of the page.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
    • idempotentHint: 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 write3
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out3
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

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

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Sign-in required, no OAuth metadata

Looked at Nov 15, 2026, 13:22 UTC, unchanged since Nov 15, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
404
tools/list served without credentials
no
Tools that change things, listed without credentials
0
Protocol version
not observed
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed

The probe stopped: initialize answered HTTP 404.

Posture changes

  1. Nov 15, 2026
    • HTTP status of an anonymous initialize: 200 to 404
    • tools/list served without credentials: yes to no
    • Protocol version: 2025-06-18 to none

Findings

Matches of fixed checks, with the text they matched.

3 info
  • The input schema at properties.url.description mentions "credentials".

    Matched text

    inputSchema.properties.url.description: "...or https:// URL. Default ports only; no credentials; no IP literals."

    What this check looks for
  • The input schema at properties.url.description mentions "credentials".

    Matched text

    inputSchema.properties.url.description: "...or https:// URL. Default ports only; no credentials; no IP literals."

    What this check looks for
  • The input schema at properties.url.description mentions "credentials".

    Matched text

    inputSchema.properties.url.description: "...or https:// URL. Default ports only; no credentials; no IP literals."

    What this check looks for

History

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

  1. PostureRemote posture changed. HTTP status of an anonymous initialize: 200 -> 404; tools/list served without credentials: yes -> no; Protocol version: 2025-06-18 -> none.View diff
    • HTTP status of an anonymous initialize: 200 to 404
    • tools/list served without credentials: yes to no
    • Protocol version: 2025-06-18 to none
  2. Tools2 changed.~2 changedView diff

Install

Pinned to version 0.2.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http agentread https://agentread.omar-cv.workers.dev/mcp
claude mcp add --transport http agentread https://agentread.omar-cv.workers.dev/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__agentread__inspect_url",
      "mcp__agentread__extract_url",
      "mcp__agentread__extract_url_structured"
    ],
    "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 agentread. Review it before you use it.

Capability tags behind 3 rules
  • mcp__agentread__inspect_url untrusted-input, outbound
  • mcp__agentread__extract_url untrusted-input, outbound
  • mcp__agentread__extract_url_structured untrusted-input, outbound

Pin

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://radar.anlyon.com/api/v1/servers/io.github.omarhassanatef/agentread/verify?hash=358b23730c6d06910784a932a89944b36224c1c2e23e9d0bef214c9c54b4ea02" | jq -e '.changed == false'

Pinned hash 358b23730c6d, from Nov 9, 2026, 00:18 UTC.

Watch

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

https://radar.anlyon.com/servers/io.github.omarhassanatef/agentread/changes.xml

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

Badge

Anlyon Radar badge for io.github.omarhassanatef/agentread
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.omarhassanatef/agentread.svg)](https://radar.anlyon.com/servers/io.github.omarhassanatef/agentread)

Source: MCP Registry · repository. Synced Oct 24, 2026, 10:18 UTC.

AgentRead MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the AgentRead MCP server safe?

No scan can promise that. What its definitions show: 3 tools, all of which only read, and 3 findings from fixed checks. Read-only tools can still pass private data to a model.

Can the AgentRead MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the AgentRead MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the AgentRead MCP server have?

3 tools: 3 read. inspect_url, extract_url and extract_url_structured.

Does the AgentRead MCP server need sign-in or OAuth?

Its remote endpoint did not answer the last anonymous look.

Does the AgentRead MCP server send data to outside services?

3 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): inspect_url, extract_url and extract_url_structured.

Has the AgentRead MCP server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Oct 24, 2026. Every change is on this page and in its Atom feed.