Skip to content

Octocrawl

by 77777R7 · remote · local (npm) · no sign-in to list tools · v0.7.0 · published by GitHub user 77777R7

Web pages as clean Markdown and JSON for AI agents, in fewer tokens, with an Evidence Record.

Read only
CompareRegistry entry

2 tools: 2 only read.

Scanned Oct 21, 2026

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

claude mcp add --transport http octocrawl https://mcp.octocrawl.dev/mcp

Tools

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

2 tools

Only reads 2Claude Code: allow
  • mapList a site's URLs without reading each page: the start page's links (read over HTTP alone) and the entries of the sitemaps the site declares, within one deadline.No findings

    Why it is in this group

    • The description's first verb is "list": a word for reading.
    Description, as the server wrote it
    List a site's URLs without reading each page: the start page's links (read over HTTP alone) and the entries of the sitemaps the site declares, within one deadline. URLs stay in scope (the start host and its www twin, the start path's subtree, assets left out, similar URLs folded) and robots.txt applies unless ignoreRobotsTxt is set; what was left out is counted. No page title is fetched. At the deadline the answer is what was found (partial, stoppedBy timeout). Compact by default; debug adds each link's evidence and the sources read. Not for: reading pages, as one page body is read at most.

    Annotations the server declares

    • title: Map a site
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • scrapeRead one URL as Markdown with its Evidence Record (final URL, fetch time, HTTP status, robots.txt decision, hashes), over HTTP first and in the browser when the page needs it.No findings

    Why it is in this group

    • The description's first verb is "read": a word for reading.
    Description, as the server wrote it
    Read one URL as Markdown with its Evidence Record (final URL, fetch time, HTTP status, robots.txt decision, hashes), over HTTP first and in the browser when the page needs it. Not for: many URLs or a whole site section. Compact by default; debug adds the full audit. warnings name what the content cannot vouch for (client_rendered_suspected, robots_overridden), and agentHints the next step.

    Annotations the server declares

    • title: Scrape a page
    • readOnlyHint: true
    • 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 0.7.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http octocrawl https://mcp.octocrawl.dev/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": [
      "mcp__octocrawl__scrape",
      "mcp__octocrawl__map"
    ],
    "ask": [],
    "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 octocrawl. Review it before you use it.