MCP Dataverse

@codeurali

Basic information

About MCP Dataverse

Give your AI agents real-time access to Dataverse — query records with OData & FetchXML, manage metadata, inspect solutions, run batch operations, audit changes, and more. Zero-config auth via Microsoft device code flow.

#dataverse #database #microsoft#power-platform#d365

MCP Dataverse config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "mcp-dataverse": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-dataverse"
      ],
      "env": {
        "DATAVERSE_ENV_URL": "<YOUR_DATAVERSE_ENV_URL>"
      }
    }
  }
}

MCP Dataverse tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

Fetch the live tool list by running this server in a temporary sandbox using the button above.

Overview

What is Mcp Dataverse?

Mcp Dataverse is a Model Context Protocol (MCP) server that gives AI assistants like Claude, Cursor, or Copilot direct access to Microsoft Dataverse environments. It is designed for Power Platform and Dynamics 365 developers who want to explore, analyze, debug, and test Dataverse environments using natural language instead of manually navigating the Power Platform interface or writing scripts.

How to use Mcp Dataverse?

Install the MCP server and configure it with your MCP-compatible client. Authentication currently uses Dataverse access tokens for development environments. Full documentation and installation instructions are available at https://codeurali.github.io/mcp-dataverse/.

Key features of Mcp Dataverse

Query Dataverse tables and records
Inspect metadata and schema
Retrieve plugin traces for debugging
Explore environment configuration
Generate structured responses for AI agents

Use cases of Mcp Dataverse

Analyzing complex Dataverse environments
Debugging production issues
Generating test data or queries
Understanding unfamiliar Dataverse schemas

Frequently asked questions

How does Mcp Dataverse differ from manually using the Power Platform interface?

It allows developers to perform Dataverse tasks using natural language AI requests instead of manually navigating the interface or writing repetitive scripts.

What authentication does Mcp Dataverse use?

It currently uses Dataverse access tokens, with future versions planned to support Azure authentication flows.

What are the runtime or dependency requirements?

It requires an MCP-compatible client (such as Claude, Cursor, or Copilot) and access to a Microsoft Dataverse environment.

Where does the data queried by Mcp Dataverse reside?

All data lives in the connected Microsoft Dataverse environment.

Are there any known limitations?

The README does not list other limitations beyond the current token-based authentication approach.

Comments

More Developer Tools MCP servers

Modelglass

Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott

LastPing

Know when your AI agents, cron jobs and CI pipelines fail, stall or go quiet. Your agent sets up monitors from a plain description, tells you what is broken and why, reads run history and traces, and writes notes on inci

Casefile

azimov777

One case file per task — shared by every session, agent and person that touches it. Self-hosted MCP server and live board. MIT.

SSH MCP Server

hypnosis

SSH MCP server for AI agents: remote commands, file transfer, log search and server audits through OpenSSH.

LocalCan

Gives AI agents public URLs (tunnels) for localhost, live HTTP traffic inspection, snapshot publishing, and access control. Part of LocalCan, the ngrok alternative for Mac, Windows and Linux. Free plan.