<rss version="2.0" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Hacker News: richardwong1</title><link>https://news.ycombinator.com/user?id=richardwong1</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Mon, 20 Apr 2026 20:40:18 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=richardwong1" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[Ask HN: How to help AI find financials in large PDF faster?]]></title><description><![CDATA[
<p>I am developing an MCP tool that is used by Claude to search company name, director and shareholders on registries of many countries. The tool might send back original PDF that contains shareholders, but the PDF is sometimes 50mb+. I want to keep the PDF original but Claude could not read the large file. But financials might be only on a couple of pages. What might be the best solution? Thx.</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47834474">https://news.ycombinator.com/item?id=47834474</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Mon, 20 Apr 2026 13:59:33 +0000</pubDate><link>https://news.ycombinator.com/item?id=47834474</link><dc:creator>richardwong1</dc:creator><comments>https://news.ycombinator.com/item?id=47834474</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47834474</guid></item><item><title><![CDATA[New comment by richardwong1 in "Show HN: OpenRegistry – MCP for global company registry search"]]></title><description><![CDATA[
<p>Example workflow:<p>Prompt:
"Find directors of Monzo Bank and show their other appointments."<p>Claude calls:<p>search_companies → get_officers → get_officer_appointments<p>This turns one company search into a full director network map.</p>
]]></description><pubDate>Mon, 20 Apr 2026 12:36:58 +0000</pubDate><link>https://news.ycombinator.com/item?id=47833389</link><dc:creator>richardwong1</dc:creator><comments>https://news.ycombinator.com/item?id=47833389</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47833389</guid></item><item><title><![CDATA[New comment by richardwong1 in "Show HN: OpenRegistry – MCP for global company registry search"]]></title><description><![CDATA[
<p>Hi — happy to answer questions.<p>This MCP server lets AI assistants query official company registries in real time. Every call goes directly to the statutory source rather than a cached dataset.<p>If anyone is building AI agents for due diligence / KYC / research, I'd love to hear what workflows you’d want supported.<p>New to MCP dev, great if any feedback or suggestion.</p>
]]></description><pubDate>Mon, 20 Apr 2026 12:35:58 +0000</pubDate><link>https://news.ycombinator.com/item?id=47833381</link><dc:creator>richardwong1</dc:creator><comments>https://news.ycombinator.com/item?id=47833381</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47833381</guid></item><item><title><![CDATA[Show HN: OpenRegistry – MCP for global company registry search]]></title><description><![CDATA[
<p>Article URL: <a href="https://github.com/sophymarine/openregistry">https://github.com/sophymarine/openregistry</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47830073">https://news.ycombinator.com/item?id=47830073</a></p>
<p>Points: 2</p>
<p># Comments: 2</p>
]]></description><pubDate>Mon, 20 Apr 2026 03:24:21 +0000</pubDate><link>https://github.com/sophymarine/openregistry</link><dc:creator>richardwong1</dc:creator><comments>https://news.ycombinator.com/item?id=47830073</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47830073</guid></item></channel></rss>