<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Query API on Work In Progress</title><link>https://www.pm50plus.co.uk/tags/query-api/</link><description>Recent content in Query API on Work In Progress</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Fri, 05 Jun 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://www.pm50plus.co.uk/tags/query-api/index.xml" rel="self" type="application/rss+xml"/><item><title>A Go SDK for the Neo4j Query API</title><link>https://www.pm50plus.co.uk/post/2026-06-05-query-api-go-sdk/</link><pubDate>Fri, 05 Jun 2026 00:00:00 +0000</pubDate><guid>https://www.pm50plus.co.uk/post/2026-06-05-query-api-go-sdk/</guid><description>&lt;p&gt;I&amp;rsquo;ve been rethinking how my MCP server talks to Neo4j for a new use case.&lt;/p&gt;
&lt;p&gt;Until now I&amp;rsquo;ve been using the full Go driver — the complete, connection-pooling, retry-aware package that&amp;rsquo;s great for working with graphs on a single Neo4j server or cluster. But I&amp;rsquo;m doing something different: an MCP server that needs to work across many graphs for many users. Think salespeople querying a customer 360 graph while production engineers explore a bill of materials graph, where you can&amp;rsquo;t assume a single Neo4j server or cluster. The driver may not be a good fit here.&lt;/p&gt;</description></item></channel></rss>