{"id":131743,"date":"2025-07-07T07:00:00","date_gmt":"2025-07-07T14:00:00","guid":{"rendered":""},"modified":"2026-02-13T08:27:55","modified_gmt":"2026-02-13T16:27:55","slug":"dataverse-mcp","status":"publish","type":"post","link":"https:\/\/www.microsoft.com\/en-us\/power-platform\/blog\/2025\/07\/07\/dataverse-mcp\/","title":{"rendered":"Dataverse MCP Server: A Game Changer for AI-Driven Workflows"},"content":{"rendered":"\n
As AI becomes integral to business workflows, the Dataverse Model Context Protocol (MCP) Server offers a foundational approach to integrating large language models with enterprise data. Whether you’re building with Microsoft Copilot Studio, Claude desktop, or GitHub Copilot in VS Code, the Dataverse MCP Server unlocks a new level of integration between AI and data.<\/p>\n\n\n\n
MCP is an open protocol that bridges large language model (LLM) applications with external data sources and tools. It acts as a bridge between AI assistants and enterprise data, enabling secure, standardized access to Dataverse resources. When Microsoft Dataverse acts as an MCP server, it enables intelligent, secure, and standardized access to your data\u2014tables, records, and more\u2014across a variety of MCP clients.<\/p>\n\n\n Dataverse MCP Server isn\u2019t just another connector\u2014it\u2019s a paradigm shift. Here\u2019s why:<\/p>\n\n\n\n MCP Clients are capable of determining the appropriate tools to use \u2013 so while the below image illustrates a workflow that an agent may take, the tools used by the MCP Client may vary from time to time.<\/p>\n\n\n Connecting is as simple as adding the Dataverse MCP Server as a tool to your agent. No local setup required. You can immediately test commands like: \u201cList tables in Dataverse\u201d, \u201cDescribe table account\u201d.<\/p>\n\n\n\n Using Dataverse MCP in Copilot studio is a compelling alternative to having agent makers using custom Dataverse connectors to manually create flows to store, update, or retrieve the data. Now, you as a maker, can simply add Dataverse MCP from the Tools tab inside an agent in Copilot Studio. Under the hood, when an agent receives user messages such as \u201cWhat is the status of my support ticket #12345\u201d, this translates to the agent calling the appropriate Dataverse MCP Tools such as determining the appropriate table to read via list_tables or describe_table, then read_query against that table.<\/p>\n\n\n\n Now makers can build dynamic, intelligent workflows with conversational agents that talk directly to Dataverse\u2014no flows, no APIs, just prompts + tools!<\/p>\n\n\n\n With a quick configuration update<\/a>, Claude can tap into your Dataverse environment. You can even toggle which tools are available per MCP server, giving you full control.<\/p>\n\n\n\n Business users often has to rely on their IT team to create dashboards. Now, with Dataverse MCP in Claude, the workflow is much streamlined. Here\u2019s an example to illustrate it.<\/p>\n\n\n\n Dataverse MCP, thus, empowers business users to explore and interact with their business data stored in Dataverse conversationally\u2014zero-code access to real-time, live insights and automation.<\/p>\n\n\n\n Reuse your Claude configuration or set up a new one<\/a>. Once connected, you can interact with Dataverse directly from VS Code GitHub Copilot in Agent mode. For example: \u201cstore the attached csv file as Employee in Dataverse\u201d. Under the hood, GitHub Copilot will automatically inspect the data and upload the data into the table \u2013 all achieved by invoking tools like list_tables, describe_table, and create_record tools to achieve this. \u00a0<\/p>\n\n\n\n With Dataverse MCP, developers see improved productivity as they don\u2019t need to open multiple portals or tools. Schema inspection, CRUD actions, and code generation happen inside the IDE!<\/p>\n\n\n\n \u26a0\ufe0f A Note on Preview Features<\/strong><\/p>\n\n\n\n This is a preview capability\u2014perfect for early adopters and innovators. While not yet production-ready, it\u2019s a fantastic opportunity to explore, experiment, and provide feedback to shape the future of AI + data integration.<\/p>\n\n\n\n We\u2019re thrilled to announce that we\u2019re bringing even more power and flexibility to Dataverse MCP! Starting end of July<\/strong>, we’re rolling out a Private Preview<\/strong> of two major capabilities:<\/p>\n\n\n\n If you’re as excited as we are and want early access, Click here to express your interest<\/a><\/strong> and be among the first to shape the future of agent-powered data platforms.<\/p>\n\n\n\n The Dataverse MCP Server represents a strategic evolution in how makers, developers, and data professionals interact with enterprise data. By enabling natural language access to Dataverse, it simplifies development and accelerates innovation across the Power Platform ecosystem and beyond.<\/p>\n\n\n\n Whether you’re designing data models, querying records, or building intelligent agents, MCP makes Dataverse the brain behind your AI.<\/p>\n\n\n\n Learn more:<\/p>\n\n\n\n <\/p>\n","protected":false},"excerpt":{"rendered":" As AI becomes integral to business workflows, the Dataverse Model Context Protocol (MCP) Server offers a foundational approach to integrating large language models with enterprise data. Whether you’re building with Microsoft Copilot Studio, Claude desktop, or GitHub Copilot in VS Code, the Dataverse MCP Server unlocks a new level of integration between AI and data.<\/p>\n","protected":false},"author":465,"featured_media":131760,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"ms_queue_id":[],"ep_exclude_from_search":false,"_classifai_error":"","_classifai_text_to_speech_error":"","_alt_title":"","ms-ems-related-posts":[],"footnotes":""},"audience":[3378],"content-type":[3424],"job-role":[],"product":[3485,3484,3390],"property":[],"topic":[],"coauthors":[3479],"class_list":["post-131743","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","audience-it-professional","content-type-news","product-copilot-studio","product-dataverse-mcp","product-microsoft-dataverse","review-flag-1593580420-967","review-flag-1-1593580433-195","review-flag-click-1593580717-121","review-flag-disco-1593580332-391","review-flag-new-1593580248-627","review-flag-priva-1593580767-323","review-flag-the-p-1680214387-540"],"yoast_head":"\n
<\/figure>\n\n\n\nWhy It Matters<\/h2>\n\n\n\n
\n
<\/figure>\n\n\n\n
<\/figure>\n\n\n\nWorks Across Your Favorite MCP Hosts and Clients<\/h2>\n\n\n\n
Microsoft Copilot Studio<\/h3>\n\n\n\n
<\/figure>\n\n\n\nClaude Desktop<\/h3>\n\n\n\n
\n
<\/figure>\n\n\n\nGitHub Copilot in VS Code<\/h3>\n\n\n\n
<\/figure>\n\n\n\nComing Soon: Remote MCP Server + Full Table Operations!<\/h3>\n\n\n\n
\n
Final Thoughts<\/h2>\n\n\n\n
\n