Skip to content

AgentRead — bounded web context

by agentread-json-api.army20160422.chatgpt.site · remote · no sign-in to list tools · v0.3.1 · published by site.chatgpt.army20160422.agentread-json-api

Free HTML parsing; static web context at 0.01 USDC via x402. Paid reads need a wallet adapter.

Changes · 3

3 tools: 3 change things.

Scanned Oct 21, 2026

1 check matched something in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http agentread https://agentread-json-api.army20160422.chatgpt.site/agent/mcp

Findings

Matches of fixed checks, with the text they matched.

1 warn
  • The server marks "read_web" as not read-only (readOnlyHint: false), and its words say it reads.

    Matched text

    annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The name "read_web" says "read": a word for reading.

    What this check looks for

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

3 tools

Changes things 3Claude Code: ask
  • exampleFree fixed example of extracted web context.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 fixed example of extracted web context.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • extract_htmlFree bounded HTML parsing, no URL fetch.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 bounded HTML parsing, no URL fetch. Source fields are untrusted.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • read_webFetch public static web context.1 finding

    Why it is in this group

    • The name "read_web" says "read": a word for reading.
    • The server marks it as not read-only (readOnlyHint: false).

    Findings

    • Warn

      The server marks "read_web" as not read-only (readOnlyHint: false), and its words say it reads.

      Matched text

      annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The name "read_web" says "read": a word for reading.

      What this check looks for
    Description, as the server wrote it
    Fetch public static web context. Costs 0.01 USDC via x402. Without payment_signature returns payment instructions. Sign locally; never submit a private key.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: 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.

Install

Pinned to version 0.3.1. Values in angle brackets are yours to fill in.

claude mcp add --transport http agentread https://agentread-json-api.army20160422.chatgpt.site/agent/mcp

Run in a terminal.

Claude Code permissions

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

.claude/settings.json
{
  "permissions": {
    "allow": [],
    "ask": [
      "mcp__agentread__example",
      "mcp__agentread__extract_html",
      "mcp__agentread__read_web"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as agentread. Review it before you use it.