{"id":134369,"date":"2026-06-08T08:51:30","date_gmt":"2026-06-08T15:51:30","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/power-platform\/blog\/?p=134369"},"modified":"2026-06-08T09:48:03","modified_gmt":"2026-06-08T16:48:03","slug":"dataverse-mcp-server-understanding-the-new-tool-shape","status":"publish","type":"post","link":"https:\/\/www.microsoft.com\/en-us\/power-platform\/blog\/2026\/06\/08\/dataverse-mcp-server-understanding-the-new-tool-shape\/","title":{"rendered":"Dataverse MCP Server: Understanding the New Tool Shape"},"content":{"rendered":"\n

The Dataverse MCP server continues to evolve. The latest Dataverse MCP updates help agents achieve more with business data through a clearer and more capable tool surface. With these changes, agents can more easily inspect metadata, query records, search across structured and unstructured data, and work with Dataverse data through well-defined tool boundaries.<\/p>\n\n\n\n

This matters because MCP already gives makers and developers a consistent way to connect agents to real business data without every client needing a custom Dataverse integration. Our enhancements ensure the Dataverse MCP experience is easier to reason about through a clearer tool shape. Agent surfaces like Copilot Studio, GitHub Copilot in VS Code, GitHub Copilot CLI, Claude Desktop, Claude Code, and other MCP-compatible clients can now connect to the Dataverse MCP endpoint and experience this new tool shape.<\/p>\n\n\n\n

<\/p>\n\n\n\n

What changed<\/h2>\n\n\n\n

The important change is not that Dataverse supports MCP. It already does. The change is that the experience is now easier to understand through a concrete set of tools. Instead of thinking about MCP as a generic connection, we can now talk about the actual tools an agent can use. The Dataverse MCP server exposes tools for common data and metadata tasks, including:<\/p>\n\n\n

\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n
Tool<\/th>\nDescription<\/th>\n<\/tr>\n<\/thead>\n
search_data<\/code><\/td>\nSearch structured and unstructured data.<\/td>\n<\/tr>\n
search<\/code><\/td>\nSearch table schemas and business skills by keyword.<\/td>\n<\/tr>\n
create_record<\/code><\/td>\nInserts a new row into a Dataverse table and returns the GUID.<\/td>\n<\/tr>\n
update_record<\/code><\/td>\nUpdates an existing row in a Dataverse table.<\/td>\n<\/tr>\n
delete_record<\/code><\/td>\nDelete a row, only after explicit user approval.<\/td>\n<\/tr>\n
create_table<\/code><\/td>\nCreates a new table with a specified schema.<\/td>\n<\/tr>\n
update_table<\/code><\/td>\nModifies schema or metadata of an existing table.<\/td>\n<\/tr>\n
delete_table<\/code><\/td>\nDeletes a table from Dataverse, only after explicit user approval.<\/td>\n<\/tr>\n
read_query<\/code><\/td>\nRun supported Dataverse SQL SELECT queries.<\/td>\n<\/tr>\n
describe<\/code><\/td>\nGet details from search results for tables, records, schemas, skills, and apps.<\/td>\n<\/tr>\n
upsert_skill<\/code><\/td>\nAdd or update a Dataverse skill\/playbook.<\/td>\n<\/tr>\n
delete_skill<\/code><\/td>\nDelete a Dataverse skill\/playbook by name.<\/td>\n<\/tr>\n
init_file_upload<\/code><\/td>\nGenerate a SAS URL for file upload.<\/td>\n<\/tr>\n
commit_file_upload<\/code><\/td>\nCommit a file upload.<\/td>\n<\/tr>\n
file_download<\/code><\/td>\nGenerate a SAS URL for file download.<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/figure>\n\n\n

This tool shape is important because it defines the contract between the agent and Dataverse. The agent is not just connected to Dataverse in a broad sense. It has a set of named capabilities that can be reasoned about, allowed, blocked, audited, and improved over time.<\/p>\n\n\n\n

For additional information, please see the documentation for full list of Dataverse MCP tools and billing rates<\/a>.<\/p>\n\n\n\n

Why the tool shape matters<\/h2>\n\n\n\n

For users, makers, and pro developers, the MCP tool shape creates a cleaner mental model.<\/p>\n\n\n\n

If an agent needs to:<\/p>\n\n\n\n