warc.html•13.9 kB
<!DOCTYPE html>
<html class="writer-html5" lang="en" data-content_root="../">
<head>
<meta charset="utf-8" /><meta name="viewport" content="width=device-width, initial-scale=1" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<title>WARC MCP Setup Guide — mcp-server-webcrawl documentation</title>
<link rel="stylesheet" type="text/css" href="../_static/pygments.css?v=80d5e7a1" />
<link rel="stylesheet" type="text/css" href="../_static/css/theme.css?v=e59714d7" />
<script src="../_static/jquery.js?v=5d32c60e"></script>
<script src="../_static/_sphinx_javascript_frameworks_compat.js?v=2cd50e6c"></script>
<script src="../_static/documentation_options.js?v=5929fcd5"></script>
<script src="../_static/doctools.js?v=888ff710"></script>
<script src="../_static/sphinx_highlight.js?v=dc90522c"></script>
<script src="../_static/js/theme.js"></script>
<link rel="index" title="Index" href="../genindex.html" />
<link rel="search" title="Search" href="../search.html" />
<link rel="next" title="wget MCP Setup Guide" href="wget.html" />
<link rel="prev" title="SiteOne MCP Setup Guide" href="siteone.html" />
</head>
<body class="wy-body-for-nav">
<div class="wy-grid-for-nav">
<nav data-toggle="wy-nav-shift" class="wy-nav-side">
<div class="wy-side-scroll">
<div class="wy-side-nav-search" >
<a href="../index.html" class="icon icon-home">
mcp-server-webcrawl
</a>
<div role="search">
<form id="rtd-search-form" class="wy-form" action="../search.html" method="get">
<input type="text" name="q" placeholder="Search docs" aria-label="Search docs" />
<input type="hidden" name="check_keywords" value="yes" />
<input type="hidden" name="area" value="default" />
</form>
</div>
</div><div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="Navigation menu">
<p class="caption" role="heading"><span class="caption-text">Contents:</span></p>
<ul class="current">
<li class="toctree-l1"><a class="reference internal" href="../installation.html">Installation</a></li>
<li class="toctree-l1 current"><a class="reference internal" href="../guides.html">Setup Guides</a><ul class="current">
<li class="toctree-l2"><a class="reference internal" href="archivebox.html">ArchiveBox MCP Setup Guide</a></li>
<li class="toctree-l2"><a class="reference internal" href="httrack.html">HTTrack MCP Setup Guide</a></li>
<li class="toctree-l2"><a class="reference internal" href="interrobot.html">InterroBot MCP Setup Guide</a></li>
<li class="toctree-l2"><a class="reference internal" href="katana.html">Katana MCP Setup Guide</a></li>
<li class="toctree-l2"><a class="reference internal" href="siteone.html">SiteOne MCP Setup Guide</a></li>
<li class="toctree-l2 current"><a class="current reference internal" href="#">WARC MCP Setup Guide</a></li>
<li class="toctree-l2"><a class="reference internal" href="wget.html">wget MCP Setup Guide</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../usage.html">Usage</a></li>
<li class="toctree-l1"><a class="reference internal" href="../prompts.html">Prompt Routines</a></li>
<li class="toctree-l1"><a class="reference internal" href="../modules.html">mcp_server_webcrawl</a></li>
</ul>
</div>
</div>
</nav>
<section data-toggle="wy-nav-shift" class="wy-nav-content-wrap"><nav class="wy-nav-top" aria-label="Mobile navigation menu" >
<i data-toggle="wy-nav-top" class="fa fa-bars"></i>
<a href="../index.html">mcp-server-webcrawl</a>
</nav>
<div class="wy-nav-content">
<div class="rst-content">
<div role="navigation" aria-label="Page navigation">
<ul class="wy-breadcrumbs">
<li><a href="../index.html" class="icon icon-home" aria-label="Home"></a></li>
<li class="breadcrumb-item"><a href="../guides.html">Setup Guides</a></li>
<li class="breadcrumb-item active">WARC MCP Setup Guide</li>
<li class="wy-breadcrumbs-aside">
<a href="../_sources/guides/warc.rst.txt" rel="nofollow"> View page source</a>
</li>
</ul>
<hr/>
</div>
<div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
<div itemprop="articleBody">
<section id="warc-mcp-setup-guide">
<h1>WARC MCP Setup Guide<a class="headerlink" href="#warc-mcp-setup-guide" title="Link to this heading"></a></h1>
<p>Instructions for setting up <a class="reference external" href="https://pragmar.com/mcp-server-webcrawl/">mcp-server-webcrawl</a> with
<a class="reference external" href="https://en.wikipedia.org/wiki/WARC_(file_format)">WARC</a> files to allow your LLM (e.g.
Claude Desktop) to search content and metadata from websites you’ve archived in WARC format.</p>
<iframe width="560" height="315" src="https://www.youtube.com/embed/fx-4WZu-UT8" frameborder="0" allowfullscreen></iframe><p>Follow along with the video, or the step-action guide below.</p>
<section id="requirements">
<h2>Requirements<a class="headerlink" href="#requirements" title="Link to this heading"></a></h2>
<p>Before you begin, ensure you have:</p>
<ul class="simple">
<li><p><a class="reference external" href="https://claude.ai/download">Claude Desktop</a> installed</p></li>
<li><p><a class="reference external" href="https://python.org">Python</a> 3.10 or later installed</p></li>
<li><p>Basic familiarity with command line interfaces</p></li>
<li><p>wget installed (macOS users can install via Homebrew, Windows users need WSL/Ubuntu)</p></li>
</ul>
</section>
<section id="what-are-warc-files">
<h2>What are WARC Files?<a class="headerlink" href="#what-are-warc-files" title="Link to this heading"></a></h2>
<p>WARC files are single-file archives that store complete crawl data including:</p>
<ul class="simple">
<li><p>HTTP status codes</p></li>
<li><p>HTTP headers</p></li>
<li><p>Response content</p></li>
</ul>
<p>Compared to wget running in mirror mode:</p>
<ul class="simple">
<li><p><strong>WARC</strong>: More comprehensive (preserves status codes and headers) but slower crawling</p></li>
<li><p><strong>wget mirror</strong>: Faster crawling but doesn’t preserve status codes or headers</p></li>
</ul>
</section>
<section id="installation-steps">
<h2>Installation Steps<a class="headerlink" href="#installation-steps" title="Link to this heading"></a></h2>
<section id="install-mcp-server-webcrawl">
<h3>1. Install mcp-server-webcrawl<a class="headerlink" href="#install-mcp-server-webcrawl" title="Link to this heading"></a></h3>
<p>Open your terminal or command line and install the package:</p>
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">pip</span> <span class="n">install</span> <span class="n">mcp</span><span class="o">-</span><span class="n">server</span><span class="o">-</span><span class="n">webcrawl</span>
</pre></div>
</div>
<p>Verify installation was successful:</p>
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">mcp</span><span class="o">-</span><span class="n">server</span><span class="o">-</span><span class="n">webcrawl</span> <span class="o">--</span><span class="n">help</span>
</pre></div>
</div>
</section>
<section id="configure-claude-desktop">
<h3>2. Configure Claude Desktop<a class="headerlink" href="#configure-claude-desktop" title="Link to this heading"></a></h3>
<ol class="arabic simple">
<li><p>Open Claude Desktop</p></li>
<li><p>Go to <strong>File → Settings → Developer → Edit Config</strong></p></li>
<li><p>Add the following configuration (modify paths as needed):</p></li>
</ol>
<div class="highlight-json notranslate"><div class="highlight"><pre><span></span><span class="p">{</span>
<span class="w"> </span><span class="nt">"mcpServers"</span><span class="p">:</span><span class="w"> </span><span class="p">{</span>
<span class="w"> </span><span class="nt">"webcrawl"</span><span class="p">:</span><span class="w"> </span><span class="p">{</span>
<span class="w"> </span><span class="nt">"command"</span><span class="p">:</span><span class="w"> </span><span class="s2">"/path/to/mcp-server-webcrawl"</span><span class="p">,</span>
<span class="w"> </span><span class="nt">"args"</span><span class="p">:</span><span class="w"> </span><span class="p">[</span><span class="s2">"--crawler"</span><span class="p">,</span><span class="w"> </span><span class="s2">"warc"</span><span class="p">,</span><span class="w"> </span><span class="s2">"--datasrc"</span><span class="p">,</span>
<span class="w"> </span><span class="s2">"/path/to/warc/archives/"</span><span class="p">]</span>
<span class="w"> </span><span class="p">}</span>
<span class="w"> </span><span class="p">}</span>
<span class="p">}</span>
</pre></div>
</div>
<div class="admonition note">
<p class="admonition-title">Note</p>
<ul class="simple">
<li><p>On Windows, use <code class="docutils literal notranslate"><span class="pre">"mcp-server-webcrawl"</span></code> as the command</p></li>
<li><p>On macOS, use the absolute path (output of <code class="docutils literal notranslate"><span class="pre">which</span> <span class="pre">mcp-server-webcrawl</span></code>)</p></li>
<li><p>Change <code class="docutils literal notranslate"><span class="pre">/path/to/warc/archives/</span></code> to your actual directory path where WARC files are stored</p></li>
</ul>
</div>
<ol class="arabic simple" start="4">
<li><p>Save the file and <strong>completely exit</strong> Claude Desktop (not just close the window)</p></li>
<li><p>Restart Claude Desktop</p></li>
</ol>
</section>
<section id="create-warc-files-with-wget">
<h3>3. Create WARC Files with Wget<a class="headerlink" href="#create-warc-files-with-wget" title="Link to this heading"></a></h3>
<ol class="arabic simple">
<li><p>Open Terminal (macOS) or Ubuntu/WSL (Windows)</p></li>
<li><p>Navigate to your target directory for storing WARC files</p></li>
<li><p>Run wget with WARC options:</p></li>
</ol>
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span><span class="c1"># basic WARC capture</span>
wget<span class="w"> </span>--warc-file<span class="o">=</span>example<span class="w"> </span>--recursive<span class="w"> </span>https://example.com
<span class="c1"># more comprehensive capture with page requirements (CSS, images, etc.)</span>
wget<span class="w"> </span>--warc-file<span class="o">=</span>example<span class="w"> </span>--recursive<span class="w"> </span>--page-requisites<span class="w"> </span>https://example.com
</pre></div>
</div>
<p>Your WARC files will be created with a .warc.gz extension in your current directory.</p>
</section>
<section id="verify-and-use">
<h3>4. Verify and Use<a class="headerlink" href="#verify-and-use" title="Link to this heading"></a></h3>
<ol class="arabic">
<li><p>In Claude Desktop, you should now see MCP tools available under Search and Tools</p></li>
<li><p>Ask Claude to list your crawled sites:</p>
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span>Can you list the crawled sites available?
</pre></div>
</div>
</li>
<li><p>Try searching content from your crawls:</p>
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span>Can you find information about [topic] on [crawled site]?
</pre></div>
</div>
</li>
</ol>
</section>
</section>
<section id="troubleshooting">
<h2>Troubleshooting<a class="headerlink" href="#troubleshooting" title="Link to this heading"></a></h2>
<ul class="simple">
<li><p>If Claude doesn’t show MCP tools after restart, verify your configuration file is correctly formatted</p></li>
<li><p>Ensure Python and mcp-server-webcrawl are properly installed</p></li>
<li><p>Check that your WARC directory path in the configuration is correct</p></li>
<li><p>Make sure your WARC files have the correct extension (typically .warc.gz)</p></li>
<li><p>Remember that the first time you use each function, Claude will ask for permission</p></li>
<li><p>For large WARC files, initial indexing may take some time</p></li>
</ul>
<p>For more details, including API documentation and other crawler options, visit the <a class="reference external" href="https://github.com/pragmar/mcp-server-webcrawl">mcp-server-webcrawl documentation</a>.</p>
</section>
</section>
</div>
</div>
<footer><div class="rst-footer-buttons" role="navigation" aria-label="Footer">
<a href="siteone.html" class="btn btn-neutral float-left" title="SiteOne MCP Setup Guide" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left" aria-hidden="true"></span> Previous</a>
<a href="wget.html" class="btn btn-neutral float-right" title="wget MCP Setup Guide" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right" aria-hidden="true"></span></a>
</div>
<hr/>
<div role="contentinfo">
<p>© Copyright 2025, pragmar.</p>
</div>
Built with <a href="https://www.sphinx-doc.org/">Sphinx</a> using a
<a href="https://github.com/readthedocs/sphinx_rtd_theme">theme</a>
provided by <a href="https://readthedocs.org">Read the Docs</a>.
</footer>
</div>
</div>
</section>
</div>
<script>
jQuery(function () {
SphinxRtdTheme.Navigation.enable(true);
});
</script>
</body>
</html>