<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Tools on MCP Toolbox for Databases</title><link>/integrations/cloud-sql-pg/tools/</link><description>Recent content in Tools on MCP Toolbox for Databases</description><generator>Hugo</generator><language>en-us</language><atom:link href="/integrations/cloud-sql-pg/tools/index.xml" rel="self" type="application/rss+xml"/><item><title>vector-assist-apply-spec</title><link>/integrations/cloud-sql-pg/tools/vector-assist-apply-spec/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>/integrations/cloud-sql-pg/tools/vector-assist-apply-spec/</guid><description>&lt;h2 id="about"&gt;About&lt;/h2&gt;
&lt;p&gt;The &lt;code&gt;vector-assist-apply-spec&lt;/code&gt; tool automatically executes all the SQL recommendations associated with a specific vector specification (spec_id) or table. It runs the necessary commands in the correct sequence to provision the workload, marking each step as applied once successful.&lt;/p&gt;
&lt;p&gt;Use this tool when the user has reviewed the generated recommendations from a defined (or modified) spec and is ready to apply the changes directly to their database instance to finalize the vector search setup. Under the hood, this tool connects to the target database and executes the &lt;code&gt;vector_assist.apply_spec&lt;/code&gt; function.&lt;/p&gt;</description></item><item><title>vector-assist-define-spec</title><link>/integrations/cloud-sql-pg/tools/vector-assist-define-spec/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>/integrations/cloud-sql-pg/tools/vector-assist-define-spec/</guid><description>&lt;h2 id="about"&gt;About&lt;/h2&gt;
&lt;p&gt;The &lt;code&gt;vector-assist-define-spec&lt;/code&gt; tool defines a new vector specification by capturing the user&amp;rsquo;s intent and requirements for a vector search workload. It generates a complete, ordered set of SQL recommendations required to set up the database, embeddings, and vector indexes.&lt;/p&gt;
&lt;p&gt;Use this tool at the very beginning of the vector setup process when an agent or user first wants to configure a table for vector search, generate embeddings, or create a new vector index. Under the hood, this tool connects to the target database and executes the &lt;code&gt;vector_assist.define_spec&lt;/code&gt; function to generate the necessary specifications.&lt;/p&gt;</description></item><item><title>vector-assist-generate-query</title><link>/integrations/cloud-sql-pg/tools/vector-assist-generate-query/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>/integrations/cloud-sql-pg/tools/vector-assist-generate-query/</guid><description>&lt;h2 id="about"&gt;About&lt;/h2&gt;
&lt;p&gt;The &lt;code&gt;vector-assist-generate-query&lt;/code&gt; tool generates optimized SQL queries for vector search by leveraging the metadata and vector specifications defined in a specific spec_id. It serves as the primary actionable tool for generating the executable SQL required to retrieve relevant results based on vector similarity.&lt;/p&gt;
&lt;p&gt;The tool contextually understands requirements such as distance functions, quantization, and filtering to ensure the resulting query is compatible with the corresponding vector index. Additionally, it can automatically handle iterative index scans for filtered queries and calculate the necessary search parameters (like ef_search) to meet a target recall.&lt;/p&gt;</description></item><item><title>vector-assist-modify-spec</title><link>/integrations/cloud-sql-pg/tools/vector-assist-modify-spec/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>/integrations/cloud-sql-pg/tools/vector-assist-modify-spec/</guid><description>&lt;h2 id="about"&gt;About&lt;/h2&gt;
&lt;p&gt;The &lt;code&gt;vector-assist-modify-spec&lt;/code&gt; tool modifies an existing vector specification (identified by a required &lt;code&gt;spec_id&lt;/code&gt;) with new parameters or overrides. Upon modification, it automatically recalculates and refreshes the list of generated recommendations by &lt;code&gt;vector_assist.define-spec&lt;/code&gt; to match the updated spec requirements.&lt;/p&gt;
&lt;p&gt;Use this tool when a user or agent wants to adjust or fine-tune the configuration of an already defined vector spec (such as changing the target recall, embedding model, or quantization) before actually executing the setup commands. Under the hood, this tool connects to the target database and executes the &lt;code&gt;vector_assist.modify_spec&lt;/code&gt; function to generate the updated specifications.&lt;/p&gt;</description></item></channel></rss>