{"id":27603,"date":"2025-05-28T00:56:10","date_gmt":"2025-05-28T07:56:10","guid":{"rendered":"https:\/\/www.pingcap.com\/?p=27603"},"modified":"2025-11-14T06:37:35","modified_gmt":"2025-11-14T14:37:35","slug":"building-intelligent-ai-agents-a-new-data-application-paradigm-with-mcp-and-tidb","status":"publish","type":"post","link":"https:\/\/www.pingcap.com\/ko\/blog\/building-intelligent-ai-agents-a-new-data-application-paradigm-with-mcp-and-tidb\/","title":{"rendered":"Building Intelligent AI Agents: A New Data Application Paradigm with MCP and TiDB"},"content":{"rendered":"<p>We&#8217;ve entered the Agentic AI Era\u2014a new phase where large language models (LLMs) go beyond understanding instructions to actively making decisions and autonomously executing tasks. In this landscape, the ability to efficiently integrate LLMs with external systems, particularly databases, has become critical for building truly powerful <a href=\"https:\/\/www.pingcap.com\/ko\/ai\/\">AI applications<\/a>.<\/p>\n\n\n\n<p>The Model Context Protocol (MCP) has emerged as the standard bridge connecting LLMs and external data sources or tool systems. It simplifies access to external resources, allowing developers to inject real-time data and executable functionality into LLM applications in a unified way.<\/p>\n\n\n\n<p>Today, we&#8217;re <strong>excited to announce that <a href=\"https:\/\/pingcap.github.io\/pytidb\">PyTiDB<\/a><\/strong>\u2014our AI SDK for <a href=\"\/ko\/tidb-cloud-starter\/\">\ud2f0DB<\/a> with vector storage and AI-powered search capabilities\u2014<strong>now offers native support for the MCP protocol<\/strong>. This integration eliminates the need to build complex plugins or custom APIs. With a simple <a href=\"https:\/\/pingcap.github.io\/pytidb\/integrations\/mcp\/\">MCP server<\/a> configuration, your TiDB resources become directly accessible within popular agent platforms like Claude Desktop and Cursor, empowering <a href=\"https:\/\/www.pingcap.com\/ko\/ai\/\">AI agents<\/a> with enhanced memory, analytical reasoning, and action-taking abilities.<\/p>\n\n\n\n<p>In this post, we\u2019ll dive deep into the core mechanisms behind MCP and TiDB\u2019s role within the MCP ecosystem. We&#8217;ll also explore a <a href=\"https:\/\/github.com\/pingcap\/pytidb\/tree\/main\/pytidb\/ext\/mcp\">practical example with complete source code<\/a> that shows how to build an intelligent data analysis app powered by TiDB and MCP.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"What_is_Model_Context_Protocol_MCP\"><\/span>What is Model Context Protocol (MCP)?<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<p>The MCP (Model Context Protocol) is an open standard that defines <a href=\"https:\/\/docs.anthropic.com\/en\/docs\/agents-and-tools\/mcp\">how LLMs can access external data and tools<\/a>.<\/p>\n\n\n\n<p><strong>How MCP Works: The Three Core Components<\/strong><\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>MCP Host<\/strong>: The LLM platform that wants to access external data (e.g., Claude Desktop, Cursor).<\/li>\n\n\n\n<li><strong>MCP Client<\/strong>: A host can include multiple MCP clients, each maintaining a one-on-one connection with an MCP server.<\/li>\n\n\n\n<li><strong>MCP Server<\/strong>: Handles real requests, communicates with external systems (e.g., databases, APIs), and returns the results to the model.<\/li>\n<\/ul>\n\n\n<div class=\"wp-block-image\">\n<figure class=\"aligncenter size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"468\" src=\"https:\/\/static.pingcap.com\/files\/2025\/05\/28002953\/The-Architecture-of-MCP-Protocol-And-The-Role-of-TiDB-In-It-1024x468.png\" alt=\"Architecture of MCP And TiDB\" class=\"wp-image-27604\" srcset=\"https:\/\/static.pingcap.com\/files\/2025\/05\/28002953\/The-Architecture-of-MCP-Protocol-And-The-Role-of-TiDB-In-It-1024x468.png 1024w, https:\/\/static.pingcap.com\/files\/2025\/05\/28002953\/The-Architecture-of-MCP-Protocol-And-The-Role-of-TiDB-In-It-300x137.png 300w, https:\/\/static.pingcap.com\/files\/2025\/05\/28002953\/The-Architecture-of-MCP-Protocol-And-The-Role-of-TiDB-In-It-768x351.png 768w, https:\/\/static.pingcap.com\/files\/2025\/05\/28002953\/The-Architecture-of-MCP-Protocol-And-The-Role-of-TiDB-In-It-1536x701.png 1536w, https:\/\/static.pingcap.com\/files\/2025\/05\/28002953\/The-Architecture-of-MCP-Protocol-And-The-Role-of-TiDB-In-It.png 1686w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><figcaption class=\"wp-element-caption\"><em>The Architecture of MCP Protocol And TiDB&#8217;s Role<\/em><\/figcaption><\/figure>\n<\/div>\n\n\n<p><strong>Why MCP Matters: Key Benefits<\/strong><\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>Breaks Down Data Silos: <\/strong>MCP bridges the gap between <a href=\"https:\/\/www.pingcap.com\/ko\/ai\/\">\uc77c\uccb4 \ud3ec\ud568<\/a> applications and external systems like databases, enabling LLMs to work with up-to-date, real-time data instead of outdated training sets.<\/li>\n\n\n\n<li><strong>Evolves<\/strong><strong> Chatbots <\/strong><strong>in<\/strong><strong>to True Agents<\/strong><strong>: <\/strong>MCP fosters integration with third-party tools, accelerating the evolution from static chatbots to autonomous agents with perception, decision-making, and action capabilities.<\/li>\n\n\n\n<li><strong>No Need for Custom Agent Plugins<\/strong><strong>: <\/strong>With a unified protocol, each external tool only needs to implement one MCP server. This avoids repeated integration efforts for each AI platform.<\/li>\n<\/ul>\n\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"Demo_GitHub_Data_Insights_with_TiDB_and_MCP\"><\/span>Demo: GitHub Data Insights with TiDB and MCP<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<p>In the past, we stored over <strong>9 billion public GitHub event records<\/strong> in TiDB for the <a href=\"https:\/\/ossinsight.io\/\">OSSInsight project<\/a>, offering pre-written SQL-based analytics and online dashboards. Today, the development pattern for data applications is shifting.<\/p>\n\n\n\n<p>With the <a href=\"https:\/\/pingcap.github.io\/pytidb\/integrations\/mcp\/\">TiDB MCP Server<\/a>, developers can now:<\/p>\n\n\n\n<p><strong>1. Easily Implement Agentic Workflows<\/strong><strong>: <\/strong>Traditional Text-to-SQL apps tend to generate errors in fixed workflows. In contrast, an AI agent connected to a database can automatically retry or correct SQL queries based on feedback\u2014dramatically reducing manual intervention.<\/p>\n\n\n\n<p><strong>2. Enable Continuous Learning for AI<\/strong><strong>: <\/strong>New-generation AI tools include memory modules to record user preferences. Over time, the LLM becomes better at generating accurate SQL queries, tailored to user intent.<\/p>\n\n\n\n<p>To see this in action, we configured the TiDB MCP Server in Claude Desktop and connected it to OSSInsight\u2019s read-only TiDB cluster. We then prompted the AI agent with this request:<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>Analyze 9 billion GitHub events stored in the TiDB database. Retrieve star history of the pingcap\/tidb repository (cumulative by year and only count the first time when the user stared) . Present the result using an ECharts line chart, and keep the explanation concise.<\/code><\/pre>\n\n\n\n<p><strong>Watch how the AI agent responds:<\/strong><\/p>\n\n\n\n<figure class=\"wp-block-video\"><video controls src=\"https:\/\/static.pingcap.com\/files\/20250528-153724.mp4\"><\/video><\/figure>\n\n\n\n<p>As shown in the video, the AI agent autonomously:<\/p>\n\n\n\n<ol start=\"1\" class=\"wp-block-list\">\n<li>Explored the database structure using tools like <code>show_tables<\/code> to understand the schema.<\/li>\n\n\n\n<li>Crafted and executed the appropriate SQL query with <code>db_query<\/code>.<\/li>\n\n\n\n<li>Transformed the raw data into a visual ECharts line chart.<\/li>\n\n\n\n<li>Delivered a concise explanation of the findings.<\/li>\n<\/ol>\n\n\n\n<p>This entire workflow happened without any manual coding or database expertise required from the user\u2014demonstrating how AI agents can make complex data analysis accessible through natural language.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"Try_TiDB_MCP_Server_Yourself\"><\/span>Try TiDB MCP Server Yourself<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<p>Let\u2019s walk through running the TiDB MCP Server step by step, which allows you to interact with the database and gain insights directly through the MCP Client.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">Prerequisites<\/h3>\n\n\n\n<ul class=\"wp-block-list\">\n<li>An MCP-compatible client (e.g., Claude Desktop, Cursor, Cline, DeepChat, ChatWise).<\/li>\n\n\n\n<li>A TiDB database cluster for testing (\ud83d\udc49 <a href=\"https:\/\/tidbcloud.com\/free-trial\">Create a free Serverless cluster on TiDB Cloud<\/a>).<\/li>\n\n\n\n<li>Sample data prepared (TiDB Cloud provides a lightweight sample dataset of GitHub repositories. You can follow the steps in the screenshot below to import it.)<\/li>\n<\/ul>\n\n\n<div class=\"wp-block-image\">\n<figure class=\"aligncenter size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"556\" src=\"https:\/\/static.pingcap.com\/files\/2025\/05\/28004532\/data-sample-1024x556.png\" alt=\"sample dataset of GitHub repositories\" class=\"wp-image-27605\" srcset=\"https:\/\/static.pingcap.com\/files\/2025\/05\/28004532\/data-sample-1024x556.png 1024w, https:\/\/static.pingcap.com\/files\/2025\/05\/28004532\/data-sample-300x163.png 300w, https:\/\/static.pingcap.com\/files\/2025\/05\/28004532\/data-sample-768x417.png 768w, https:\/\/static.pingcap.com\/files\/2025\/05\/28004532\/data-sample-1536x833.png 1536w, https:\/\/static.pingcap.com\/files\/2025\/05\/28004532\/data-sample-2048x1111.png 2048w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><figcaption class=\"wp-element-caption\"><em>Sample Dataset of GitHub Repositories<\/em><\/figcaption><\/figure>\n<\/div>\n\n\n<h3 class=\"wp-block-heading\">Setup Steps<\/h3>\n\n\n\n<p>For comprehensive documentation, please visit <a href=\"https:\/\/pingcap.github.io\/pytidb\/integrations\/mcp\">https:\/\/pingcap.github.io\/pytidb\/integrations\/mcp<\/a> .<\/p>\n\n\n\n<ol start=\"1\" class=\"wp-block-list\">\n<li>Clone the MCP repo:<\/li>\n<\/ol>\n\n\n\n<pre class=\"wp-block-code\"><code>git clone https:\/\/github.com\/pingcap\/pytidb\ncd pytidb<\/code><\/pre>\n\n\n\n<ol start=\"2\" class=\"wp-block-list\">\n<li>Install dependencies<\/li>\n<\/ol>\n\n\n\n<p>We recommended using the <code><a href=\"https:\/\/docs.astral.sh\/uv\/getting-started\/installation\/\">uv<\/a><\/code> package manager for the best experience:<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>uv sync --extra mcp<\/code><\/pre>\n\n\n\n<ol start=\"3\" class=\"wp-block-list\">\n<li>In Claude Desktop, go to <code>Settings -&gt; Developer -&gt; Edit Config<\/code> and open the configuration file:<\/li>\n<\/ol>\n\n\n<div class=\"wp-block-image\">\n<figure class=\"aligncenter size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"704\" src=\"https:\/\/static.pingcap.com\/files\/2025\/05\/28004744\/Snipaste_2025-05-21_16-55-07-1024x704.png\" alt=\"Claude Desktop Setting\" class=\"wp-image-27606\" srcset=\"https:\/\/static.pingcap.com\/files\/2025\/05\/28004744\/Snipaste_2025-05-21_16-55-07-1024x704.png 1024w, https:\/\/static.pingcap.com\/files\/2025\/05\/28004744\/Snipaste_2025-05-21_16-55-07-300x206.png 300w, https:\/\/static.pingcap.com\/files\/2025\/05\/28004744\/Snipaste_2025-05-21_16-55-07-768x528.png 768w, https:\/\/static.pingcap.com\/files\/2025\/05\/28004744\/Snipaste_2025-05-21_16-55-07-1536x1057.png 1536w, https:\/\/static.pingcap.com\/files\/2025\/05\/28004744\/Snipaste_2025-05-21_16-55-07.png 1890w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><figcaption class=\"wp-element-caption\"><em>Claude Desktop Setting<\/em><\/figcaption><\/figure>\n<\/div>\n\n\n<ol start=\"4\" class=\"wp-block-list\">\n<li>Add the TiDB MCP server config:<\/li>\n<\/ol>\n\n\n\n<p>You can find the database connection parameters on the cluster details page in TiDB Cloud.<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>{\n  \"mcpServers\": {\n    \"tidb\": {\n      \"command\": \"uv\",\n      \"args\": &#91;\n        \"--directory\",\n        \"\/path\/to\/pytidb\",\n        \"run\",\n        \"-m\",\n        \"pytidb.ext.mcp\"\n      ],\n      \"env\": {\n        \"TIDB_HOST\": \"{host}\",\n        \"TIDB_PORT\": \"4000\",\n        \"TIDB_USERNAME\": \"{username}\",\n        \"TIDB_PASSWORD\": \"{password}\",\n        \"TIDB_DATABASE\": \"{database}\"\n      }\n    }\n  }\n}<\/code><\/pre>\n\n\n\n<ol start=\"5\" class=\"wp-block-list\">\n<li>Restart Claude Desktop. You\u2019ll see the TiDB MCP Server tools listed in the agent\u2019s tool panel.<\/li>\n<\/ol>\n\n\n<div class=\"wp-block-image\">\n<figure class=\"aligncenter size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"659\" src=\"https:\/\/static.pingcap.com\/files\/2025\/05\/28005016\/Snipaste_2025-05-21_17-37-18-1024x659.png\" alt=\"Agent's tool panel\" class=\"wp-image-27607\" srcset=\"https:\/\/static.pingcap.com\/files\/2025\/05\/28005016\/Snipaste_2025-05-21_17-37-18-1024x659.png 1024w, https:\/\/static.pingcap.com\/files\/2025\/05\/28005016\/Snipaste_2025-05-21_17-37-18-300x193.png 300w, https:\/\/static.pingcap.com\/files\/2025\/05\/28005016\/Snipaste_2025-05-21_17-37-18-768x494.png 768w, https:\/\/static.pingcap.com\/files\/2025\/05\/28005016\/Snipaste_2025-05-21_17-37-18-1536x988.png 1536w, https:\/\/static.pingcap.com\/files\/2025\/05\/28005016\/Snipaste_2025-05-21_17-37-18-2048x1318.png 2048w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><figcaption class=\"wp-element-caption\"><em>Agent&#8217;s Tool Panel<\/em><\/figcaption><\/figure>\n<\/div>\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"Looking_Ahead\"><\/span>Looking Ahead<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<p>The Model Context Protocol is rapidly establishing itself as the standard interface between AI models and external systems. By creating this universal communication layer, MCP allows AI model providers to focus on enhancing core capabilities while enabling tool developers to build once and deploy across multiple AI platforms.<\/p>\n\n\n\n<p>The release of the TiDB MCP Server marks a significant step forward in our AI ecosystem strategy. We&#8217;re excited to see what you&#8217;ll create with these capabilities!<\/p>\n\n\n\n<p>If you have any questions or want to share what you&#8217;re building, join our <a href=\"https:\/\/discord.gg\/zcqexutz2R\">community on Discord<\/a> where our team and other developers are ready to help. Your feedback directly shapes TiDB and makes it better for everyone.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Additional <\/strong><strong>Resources:<\/strong><\/h3>\n\n\n\n<ul class=\"wp-block-list\">\n<li>TiDB Vector Search for Generative AI: <a href=\"https:\/\/www.pingcap.com\/ko\/ai\/\">https:\/\/www.pingcap.com\/ai\/<\/a><\/li>\n\n\n\n<li>Code: <a href=\"https:\/\/github.com\/pingcap\/pytidb\/tree\/main\/pytidb\/ext\">https:\/\/github.com\/pingcap\/pytidb\/tree\/main\/pytidb\/ext<\/a><\/li>\n\n\n\n<li>Documentation: <a href=\"https:\/\/pingcap.github.io\/pytidb\/integrations\/mcp\/#database-management\">https:\/\/pingcap.github.io\/pytidb\/integrations\/mcp<\/a><\/li>\n<\/ul>\n\n\n\n<p><\/p>","protected":false},"excerpt":{"rendered":"<p>We&#8217;ve entered the Agentic AI Era\u2014a new phase where large language models (LLMs) go beyond understanding instructions to actively making decisions and autonomously executing tasks. In this landscape, the ability to efficiently integrate LLMs with external systems, particularly databases, has become critical for building truly powerful AI applications. The Model Context Protocol (MCP) has emerged [&hellip;]<\/p>\n","protected":false},"author":196,"featured_media":27624,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"ub_ctt_via":"","footnotes":""},"categories":[13],"tags":[147,405,407,208,297],"class_list":["post-27603","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-product","tag-distributed-sql","tag-genai","tag-mcp","tag-tidb-serverless","tag-vector-search"],"acf":[],"featured_image_src":"https:\/\/static.pingcap.com\/files\/2025\/05\/28031419\/MCP-and-TiDB-banner-scaled.png","author_info":{"display_name":"Zhiyuan Liang","author_link":"https:\/\/www.pingcap.com\/ko\/blog\/author\/zhiyuan-liang\/"},"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v26.9 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>MCP and TiDB: Powering Intelligent AI Agent Development<\/title>\n<meta name=\"description\" content=\"In this post, we\u2019ll dive deep into the core mechanisms behind MCP and explore TiDB\u2019s role within the broader MCP ecosystem.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.pingcap.com\/ko\/blog\/building-intelligent-ai-agents-a-new-data-application-paradigm-with-mcp-and-tidb\/\" \/>\n<meta property=\"og:locale\" content=\"ko_KR\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"MCP and TiDB: Powering Intelligent AI Agent Development\" \/>\n<meta property=\"og:description\" content=\"In this post, we\u2019ll dive deep into the core mechanisms behind MCP and explore TiDB\u2019s role within the broader MCP ecosystem.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.pingcap.com\/ko\/blog\/building-intelligent-ai-agents-a-new-data-application-paradigm-with-mcp-and-tidb\/\" \/>\n<meta property=\"og:site_name\" content=\"TiDB\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/facebook.com\/pingcap2015\" \/>\n<meta property=\"article:published_time\" content=\"2025-05-28T07:56:10+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2025-11-14T14:37:35+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/static.pingcap.com\/files\/2025\/05\/28031401\/MCP-and-TiDB-scaled.png\" \/>\n\t<meta property=\"og:image:width\" content=\"2560\" \/>\n\t<meta property=\"og:image:height\" content=\"1280\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\n<meta name=\"author\" content=\"Zhiyuan Liang\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:image\" content=\"https:\/\/static.pingcap.com\/files\/2025\/05\/28031401\/MCP-and-TiDB-scaled.png\" \/>\n<meta name=\"twitter:creator\" content=\"@PingCAP\" \/>\n<meta name=\"twitter:site\" content=\"@PingCAP\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Zhiyuan Liang\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"5\ubd84\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/www.pingcap.com\/blog\/building-intelligent-ai-agents-a-new-data-application-paradigm-with-mcp-and-tidb\/#article\",\"isPartOf\":{\"@id\":\"https:\/\/www.pingcap.com\/blog\/building-intelligent-ai-agents-a-new-data-application-paradigm-with-mcp-and-tidb\/\"},\"author\":{\"name\":\"Zhiyuan Liang\",\"@id\":\"https:\/\/www.pingcap.com\/#\/schema\/person\/eb40ba298bc36a0f833ac79b7f473b0e\"},\"headline\":\"Building Intelligent AI Agents: A New Data Application Paradigm with MCP and TiDB\",\"datePublished\":\"2025-05-28T07:56:10+00:00\",\"dateModified\":\"2025-11-14T14:37:35+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/www.pingcap.com\/blog\/building-intelligent-ai-agents-a-new-data-application-paradigm-with-mcp-and-tidb\/\"},\"wordCount\":960,\"publisher\":{\"@id\":\"https:\/\/www.pingcap.com\/#organization\"},\"image\":{\"@id\":\"https:\/\/www.pingcap.com\/blog\/building-intelligent-ai-agents-a-new-data-application-paradigm-with-mcp-and-tidb\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/static.pingcap.com\/files\/2025\/05\/28031419\/MCP-and-TiDB-banner-scaled.png\",\"keywords\":[\"Distributed SQL\",\"GenAI\",\"MCP\",\"TiDB Serverless\",\"Vector Search\"],\"articleSection\":[\"Product\"],\"inLanguage\":\"ko-KR\"},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.pingcap.com\/blog\/building-intelligent-ai-agents-a-new-data-application-paradigm-with-mcp-and-tidb\/\",\"url\":\"https:\/\/www.pingcap.com\/blog\/building-intelligent-ai-agents-a-new-data-application-paradigm-with-mcp-and-tidb\/\",\"name\":\"MCP and TiDB: Powering Intelligent AI Agent Development\",\"isPartOf\":{\"@id\":\"https:\/\/www.pingcap.com\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/www.pingcap.com\/blog\/building-intelligent-ai-agents-a-new-data-application-paradigm-with-mcp-and-tidb\/#primaryimage\"},\"image\":{\"@id\":\"https:\/\/www.pingcap.com\/blog\/building-intelligent-ai-agents-a-new-data-application-paradigm-with-mcp-and-tidb\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/static.pingcap.com\/files\/2025\/05\/28031419\/MCP-and-TiDB-banner-scaled.png\",\"datePublished\":\"2025-05-28T07:56:10+00:00\",\"dateModified\":\"2025-11-14T14:37:35+00:00\",\"description\":\"In this post, we\u2019ll dive deep into the core mechanisms behind MCP and explore TiDB\u2019s role within the broader MCP ecosystem.\",\"breadcrumb\":{\"@id\":\"https:\/\/www.pingcap.com\/blog\/building-intelligent-ai-agents-a-new-data-application-paradigm-with-mcp-and-tidb\/#breadcrumb\"},\"inLanguage\":\"ko-KR\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.pingcap.com\/blog\/building-intelligent-ai-agents-a-new-data-application-paradigm-with-mcp-and-tidb\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"ko-KR\",\"@id\":\"https:\/\/www.pingcap.com\/blog\/building-intelligent-ai-agents-a-new-data-application-paradigm-with-mcp-and-tidb\/#primaryimage\",\"url\":\"https:\/\/static.pingcap.com\/files\/2025\/05\/28031419\/MCP-and-TiDB-banner-scaled.png\",\"contentUrl\":\"https:\/\/static.pingcap.com\/files\/2025\/05\/28031419\/MCP-and-TiDB-banner-scaled.png\",\"width\":2560,\"height\":853,\"caption\":\"MCP and TiDB-banner\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.pingcap.com\/blog\/building-intelligent-ai-agents-a-new-data-application-paradigm-with-mcp-and-tidb\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/www.pingcap.com\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Building Intelligent AI Agents: A New Data Application Paradigm with MCP and TiDB\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.pingcap.com\/#website\",\"url\":\"https:\/\/www.pingcap.com\/\",\"name\":\"TiDB\",\"description\":\"TiDB | SQL at Scale\",\"publisher\":{\"@id\":\"https:\/\/www.pingcap.com\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.pingcap.com\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"ko-KR\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/www.pingcap.com\/#organization\",\"name\":\"PingCAP\",\"url\":\"https:\/\/www.pingcap.com\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"ko-KR\",\"@id\":\"https:\/\/www.pingcap.com\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/static.pingcap.com\/files\/2021\/11\/pingcap-logo.png\",\"contentUrl\":\"https:\/\/static.pingcap.com\/files\/2021\/11\/pingcap-logo.png\",\"width\":811,\"height\":232,\"caption\":\"PingCAP\"},\"image\":{\"@id\":\"https:\/\/www.pingcap.com\/#\/schema\/logo\/image\/\"},\"sameAs\":[\"https:\/\/facebook.com\/pingcap2015\",\"https:\/\/x.com\/PingCAP\",\"https:\/\/linkedin.com\/company\/pingcap\",\"https:\/\/youtube.com\/channel\/UCuq4puT32DzHKT5rU1IZpIA\"]},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.pingcap.com\/#\/schema\/person\/eb40ba298bc36a0f833ac79b7f473b0e\",\"name\":\"Zhiyuan Liang\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"ko-KR\",\"@id\":\"https:\/\/www.pingcap.com\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/static.pingcap.com\/files\/2022\/10\/17234942\/avatar.jpg\",\"contentUrl\":\"https:\/\/static.pingcap.com\/files\/2022\/10\/17234942\/avatar.jpg\",\"caption\":\"Zhiyuan Liang\"},\"description\":\"Senior Software Engineer\",\"url\":\"https:\/\/www.pingcap.com\/ko\/blog\/author\/zhiyuan-liang\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"MCP and TiDB: Powering Intelligent AI Agent Development","description":"In this post, we\u2019ll dive deep into the core mechanisms behind MCP and explore TiDB\u2019s role within the broader MCP ecosystem.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.pingcap.com\/ko\/blog\/building-intelligent-ai-agents-a-new-data-application-paradigm-with-mcp-and-tidb\/","og_locale":"ko_KR","og_type":"article","og_title":"MCP and TiDB: Powering Intelligent AI Agent Development","og_description":"In this post, we\u2019ll dive deep into the core mechanisms behind MCP and explore TiDB\u2019s role within the broader MCP ecosystem.","og_url":"https:\/\/www.pingcap.com\/ko\/blog\/building-intelligent-ai-agents-a-new-data-application-paradigm-with-mcp-and-tidb\/","og_site_name":"TiDB","article_publisher":"https:\/\/facebook.com\/pingcap2015","article_published_time":"2025-05-28T07:56:10+00:00","article_modified_time":"2025-11-14T14:37:35+00:00","og_image":[{"width":2560,"height":1280,"url":"https:\/\/static.pingcap.com\/files\/2025\/05\/28031401\/MCP-and-TiDB-scaled.png","type":"image\/png"}],"author":"Zhiyuan Liang","twitter_card":"summary_large_image","twitter_image":"https:\/\/static.pingcap.com\/files\/2025\/05\/28031401\/MCP-and-TiDB-scaled.png","twitter_creator":"@PingCAP","twitter_site":"@PingCAP","twitter_misc":{"Written by":"Zhiyuan Liang","Est. reading time":"5\ubd84"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/www.pingcap.com\/blog\/building-intelligent-ai-agents-a-new-data-application-paradigm-with-mcp-and-tidb\/#article","isPartOf":{"@id":"https:\/\/www.pingcap.com\/blog\/building-intelligent-ai-agents-a-new-data-application-paradigm-with-mcp-and-tidb\/"},"author":{"name":"Zhiyuan Liang","@id":"https:\/\/www.pingcap.com\/#\/schema\/person\/eb40ba298bc36a0f833ac79b7f473b0e"},"headline":"Building Intelligent AI Agents: A New Data Application Paradigm with MCP and TiDB","datePublished":"2025-05-28T07:56:10+00:00","dateModified":"2025-11-14T14:37:35+00:00","mainEntityOfPage":{"@id":"https:\/\/www.pingcap.com\/blog\/building-intelligent-ai-agents-a-new-data-application-paradigm-with-mcp-and-tidb\/"},"wordCount":960,"publisher":{"@id":"https:\/\/www.pingcap.com\/#organization"},"image":{"@id":"https:\/\/www.pingcap.com\/blog\/building-intelligent-ai-agents-a-new-data-application-paradigm-with-mcp-and-tidb\/#primaryimage"},"thumbnailUrl":"https:\/\/static.pingcap.com\/files\/2025\/05\/28031419\/MCP-and-TiDB-banner-scaled.png","keywords":["Distributed SQL","GenAI","MCP","TiDB Serverless","Vector Search"],"articleSection":["Product"],"inLanguage":"ko-KR"},{"@type":"WebPage","@id":"https:\/\/www.pingcap.com\/blog\/building-intelligent-ai-agents-a-new-data-application-paradigm-with-mcp-and-tidb\/","url":"https:\/\/www.pingcap.com\/blog\/building-intelligent-ai-agents-a-new-data-application-paradigm-with-mcp-and-tidb\/","name":"MCP and TiDB: Powering Intelligent AI Agent Development","isPartOf":{"@id":"https:\/\/www.pingcap.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.pingcap.com\/blog\/building-intelligent-ai-agents-a-new-data-application-paradigm-with-mcp-and-tidb\/#primaryimage"},"image":{"@id":"https:\/\/www.pingcap.com\/blog\/building-intelligent-ai-agents-a-new-data-application-paradigm-with-mcp-and-tidb\/#primaryimage"},"thumbnailUrl":"https:\/\/static.pingcap.com\/files\/2025\/05\/28031419\/MCP-and-TiDB-banner-scaled.png","datePublished":"2025-05-28T07:56:10+00:00","dateModified":"2025-11-14T14:37:35+00:00","description":"In this post, we\u2019ll dive deep into the core mechanisms behind MCP and explore TiDB\u2019s role within the broader MCP ecosystem.","breadcrumb":{"@id":"https:\/\/www.pingcap.com\/blog\/building-intelligent-ai-agents-a-new-data-application-paradigm-with-mcp-and-tidb\/#breadcrumb"},"inLanguage":"ko-KR","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.pingcap.com\/blog\/building-intelligent-ai-agents-a-new-data-application-paradigm-with-mcp-and-tidb\/"]}]},{"@type":"ImageObject","inLanguage":"ko-KR","@id":"https:\/\/www.pingcap.com\/blog\/building-intelligent-ai-agents-a-new-data-application-paradigm-with-mcp-and-tidb\/#primaryimage","url":"https:\/\/static.pingcap.com\/files\/2025\/05\/28031419\/MCP-and-TiDB-banner-scaled.png","contentUrl":"https:\/\/static.pingcap.com\/files\/2025\/05\/28031419\/MCP-and-TiDB-banner-scaled.png","width":2560,"height":853,"caption":"MCP and TiDB-banner"},{"@type":"BreadcrumbList","@id":"https:\/\/www.pingcap.com\/blog\/building-intelligent-ai-agents-a-new-data-application-paradigm-with-mcp-and-tidb\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.pingcap.com\/"},{"@type":"ListItem","position":2,"name":"Building Intelligent AI Agents: A New Data Application Paradigm with MCP and TiDB"}]},{"@type":"WebSite","@id":"https:\/\/www.pingcap.com\/#website","url":"https:\/\/www.pingcap.com\/","name":"\ud2f0DB","description":"TiDB | SQL at Scale","publisher":{"@id":"https:\/\/www.pingcap.com\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.pingcap.com\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"ko-KR"},{"@type":"Organization","@id":"https:\/\/www.pingcap.com\/#organization","name":"PingCAP","url":"https:\/\/www.pingcap.com\/","logo":{"@type":"ImageObject","inLanguage":"ko-KR","@id":"https:\/\/www.pingcap.com\/#\/schema\/logo\/image\/","url":"https:\/\/static.pingcap.com\/files\/2021\/11\/pingcap-logo.png","contentUrl":"https:\/\/static.pingcap.com\/files\/2021\/11\/pingcap-logo.png","width":811,"height":232,"caption":"PingCAP"},"image":{"@id":"https:\/\/www.pingcap.com\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/facebook.com\/pingcap2015","https:\/\/x.com\/PingCAP","https:\/\/linkedin.com\/company\/pingcap","https:\/\/youtube.com\/channel\/UCuq4puT32DzHKT5rU1IZpIA"]},{"@type":"Person","@id":"https:\/\/www.pingcap.com\/#\/schema\/person\/eb40ba298bc36a0f833ac79b7f473b0e","name":"Zhiyuan Liang","image":{"@type":"ImageObject","inLanguage":"ko-KR","@id":"https:\/\/www.pingcap.com\/#\/schema\/person\/image\/","url":"https:\/\/static.pingcap.com\/files\/2022\/10\/17234942\/avatar.jpg","contentUrl":"https:\/\/static.pingcap.com\/files\/2022\/10\/17234942\/avatar.jpg","caption":"Zhiyuan Liang"},"description":"Senior Software Engineer","url":"https:\/\/www.pingcap.com\/ko\/blog\/author\/zhiyuan-liang\/"}]}},"grav_blocks":false,"card_markup":"<a class=\"card-resource bg-white\" href=\"https:\/\/www.pingcap.com\/ko\/blog\/building-intelligent-ai-agents-a-new-data-application-paradigm-with-mcp-and-tidb\/\"><div class=\"card-resource__image-container\"><img class=\"card-resource__image\" alt=\"MCP and TiDB-banner\" src=\"https:\/\/static.pingcap.com\/files\/2025\/05\/28031419\/MCP-and-TiDB-banner-scaled.png\" loading=\"lazy\" width=2560 height=853 \/><\/div><div class=\"card-resource__content-container\"><div class=\"card-resource__content-head\"><div class=\"card-resource__category\">Product<\/div><\/div><h5 class=\"card-resource__title\">Building Intelligent AI Agents: A New Data Application Paradigm with MCP and TiDB<\/h5><\/div><\/a>","_links":{"self":[{"href":"https:\/\/www.pingcap.com\/ko\/wp-json\/wp\/v2\/posts\/27603","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.pingcap.com\/ko\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.pingcap.com\/ko\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.pingcap.com\/ko\/wp-json\/wp\/v2\/users\/196"}],"replies":[{"embeddable":true,"href":"https:\/\/www.pingcap.com\/ko\/wp-json\/wp\/v2\/comments?post=27603"}],"version-history":[{"count":10,"href":"https:\/\/www.pingcap.com\/ko\/wp-json\/wp\/v2\/posts\/27603\/revisions"}],"predecessor-version":[{"id":30521,"href":"https:\/\/www.pingcap.com\/ko\/wp-json\/wp\/v2\/posts\/27603\/revisions\/30521"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.pingcap.com\/ko\/wp-json\/wp\/v2\/media\/27624"}],"wp:attachment":[{"href":"https:\/\/www.pingcap.com\/ko\/wp-json\/wp\/v2\/media?parent=27603"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.pingcap.com\/ko\/wp-json\/wp\/v2\/categories?post=27603"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.pingcap.com\/ko\/wp-json\/wp\/v2\/tags?post=27603"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}