MCP Server

Maintained

MIT

MCP Dataverse MCP Server

io.github.codeurali/dataverse

79 tools for Microsoft Dataverse: CRUD, FetchXML, metadata, audit, batch, RBAC, and schema management with three auth modes.

Repository Registry

What is the MCP Dataverse MCP server?

The MCP Dataverse server is a comprehensive Model Context Protocol integration for Microsoft Dataverse that provides AI agents with real-time access to schema, records, metadata, and solutions. It exposes 79 tools across CRUD operations, FetchXML queries, role-based access control, audit logs, batch operations, and schema management, eliminating hallucinations about column names and OData queries. The server supports three authentication modes (device code, client credentials, and managed identity) and works with any MCP client including VS Code, Claude, Cursor, and Windsurf.

MCP Dataverse gives AI agents direct, real-time access to your Microsoft Dataverse environment through 79 atomic tools. Instead of guessing schema and building broken queries, agents can query tables, manage records, execute actions, handle batch operations, check audit logs, and manage role-based access control with confidence. It's designed for developers and AI workflows that need reliable Dataverse integration without hallucinations.

How to install MCP Dataverse

Copy-paste configuration for popular MCP clients.

transport: stdio

Config generated by PluginBench — verify against the source before use.

Environment / auth

MCP_CONFIG_PATH
Path to a config.json file (overrides all other env vars). Recommended for VS Code / Claude Desktop setups.
DATAVERSE_ENV_URL
Your Dataverse environment URL

~/Library/Application Support/Claude/claude_desktop_config.json

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

Tools & capabilities

Tools this server exposes to the agent.

Metadata Tools — 9 tools for querying tables, schema, relationships, option sets, and entity keys
Query Tools — 3 tools for OData, FetchXML, and paginated record retrieval
CRUD Tools — 6 tools for get, create, update, delete, upsert, and assign operations
Relations Tools — 4 tools for associate, associate bulk, disassociate, and query associations
Actions & Functions — 6 tools for bound and unbound Dataverse actions and functions
Batch Operations — 1 tool for atomic batch operations up to 1000 records
Solutions — 2 tools for publishing customizations and creating sitemaps
Full-Text Search — 1 tool for Relevance Search queries
Users & Teams — 4 tools for managing users, roles, teams, and role assignments
RBAC Tools — 7 tools for listing, assigning, removing, and managing role privileges
File Operations — 2 tools for uploading and downloading file and image columns
Audit & Trace — 3 tools for audit logs, plugin trace logs, and workflow trace logs
Annotations — 2 tools for notes and file attachments
Customization — 4 tools for custom actions, plugins, environment variables, and connection references
Attributes — 4 tools for creating, updating, deleting columns and managing lookup types
Schema Write — 2 tools for creating custom tables and relationships
Record Access — 4 tools for checking, granting, revoking record sharing and merging records
Assistance Tools — 2 tools for tool routing and tool tags

Use cases

Query Dataverse tables and retrieve records using OData or FetchXML without guessing column names or schema structure
Automate CRUD operations (create, update, delete, upsert) on Dataverse records with AI-driven workflows
Manage role-based access control by assigning and revoking privileges across users and teams
Execute batch operations atomically to update or create up to 1000 records in a single transaction
Audit and troubleshoot Dataverse changes by querying audit logs, plugin trace logs, and workflow execution history

MCP Dataverse MCP server FAQ

What is MCP Dataverse?

MCP Dataverse is an MCP server that gives AI agents like Claude and Cursor direct access to Microsoft Dataverse through 79 tools for CRUD, queries, metadata, audit logs, RBAC, batch operations, and schema management.

Is MCP Dataverse free?

Yes, MCP Dataverse is open-source under the MIT license. You only need a Microsoft Dataverse environment and Node.js 20+ to run it.

How do I install it in Cursor or Claude?

Install via npm with `npx mcp-dataverse install` for VS Code, or manually configure the server in your client's MCP settings. For multi-client setups, run it as an HTTP server and connect via the client's configuration.

What authentication methods are supported?

Three modes: Device Code (interactive login for local development), Client Credentials (for CI/CD and unattended scenarios), and Managed Identity (for Azure-hosted services).

Do I need special permissions in Dataverse?

Your Microsoft account must have access to the target Dataverse environment. Destructive operations require explicit confirmation, and the server respects your existing Dataverse role-based access control.

Can I run it as a shared server?

Yes, MCP Dataverse supports HTTP transport. Set `MCP_TRANSPORT=http` and `MCP_HTTP_PORT` to run it as a server that multiple clients can connect to simultaneously.

README (reference)

Source of truth, from the repository.

MCP Dataverse

The most complete MCP server for Microsoft Dataverse.

79 tools · 4 resources · 10 guided workflows · Three auth modes

→ Full Documentation

</div>

Why MCP Dataverse?

AI agents hallucinate schema, guess column names, and build broken OData queries. This server gives them real-time access to your Dataverse environment — schema, records, metadata, solutions — through the Model Context Protocol.

Three auth modes — device code (local), client credentials (CI/CD), managed identity (Azure-hosted)
Works with any MCP client — VS Code, Claude, Cursor, Windsurf, Gemini, Codex CLI
Atomic tools — each tool does one thing well; the AI picks the right one
Structured outputs — every response returns {summary, data, suggestions}
Guardrails — destructive operations require explicit confirmation
Encrypted tokens — AES-256-GCM cached credentials, never logged

Install

npx mcp-dataverse install

The interactive wizard configures your environment, registers the server in VS Code, and authenticates your Microsoft account in under 2 minutes.

Requires Node.js 20+. For other clients (Claude, Cursor, Windsurf…) see Multi-Client Setup.

Update

npx mcp-dataverse update

No re-config required — just checks your existing setup and shows what changed. npx auto-fetches the latest version on each run, so simply restarting your MCP client is enough to get the new tools.

Authentication

Three modes — choose based on where the server runs:

Mode	When to use
Device Code (default)	Local development — interactive Microsoft login, token cached on disk
Client Credentials	Unattended: CI/CD, Docker, Azure services — `authMethod: "client-credentials"` + App Registration
Managed Identity	Azure-hosted (App Service, Container Apps) — zero secrets, `authMethod: "managed-identity"`

Device code quick start: authentication triggers on the first tool call.

Open View → Output → MCP — a sign-in code appears
Go to https://microsoft.com/devicelogin, enter the code, sign in with your work account
Token is cached encrypted — all future starts are silent

For client credentials and managed identity setup, see Authentication docs.

Capabilities

Category	Count	Description
Metadata	9	Tables, schema, relationships, option sets, entity keys
Query	3	OData, FetchXML, paginated retrieval
CRUD	6	Get, create, update, delete, upsert, assign
Relations	4	Associate, associate bulk, disassociate, query associations
Actions & Functions	6	Bound/unbound Dataverse actions and functions
Batch	1	Up to 1000 operations atomically
Solutions	2	Publish customizations, create sitemap
Search	1	Full-text Relevance Search
Users & Teams	4	Users, roles, teams, role assignment
RBAC	7	Role privileges: list, assign, remove, add, replace, get, team
Files	2	Upload/download file and image columns
Audit & Trace	3	Audit log, plugin trace logs, workflow trace logs
Annotations	2	Notes and file attachments
Customization	4	Custom actions, plugins, env variables, connection references
Attributes	4	Create, update, delete columns; lookup column type
Schema (write)	2	Create custom tables and relationships
Record Access	4	Check, grant, revoke record sharing; merge records
Assistance	2	Tool router, tool tags
+ more	…	Delta sync, impersonation, views, business units, duplicate detection

→ Full Capabilities Reference

HTTP Transport

Run as an HTTP server for multi-client use:

MCP_TRANSPORT=http MCP_HTTP_PORT=3000 MCP_HTTP_SECRET=mysecret node dist/server.js

Connect using VS Code / Copilot with:

{
  "servers": {
    "dataverse": {
      "type": "http",
      "url": "http://localhost:3000/mcp",
      "headers": {
        "Authorization": "Bearer mysecret"
      }
    }
  }
}

Troubleshooting

Symptom	Fix
No sign-in prompt	Open View → Output → MCP — the device code is displayed there
`No MSAL accounts found`	Run `npx mcp-dataverse-auth` then restart the server
`Authentication timed out`	Restart the MCP server — a fresh code is generated automatically
Server not appearing in Agent mode	Run `npx mcp-dataverse install` or `npx mcp-dataverse doctor`
HTTP errors	Run `npx mcp-dataverse doctor` to diagnose config and connectivity

Performance Tip

MCP Dataverse is designed to be comprehensive, but most AI models work best with fewer tools in context. Deselect the tools you don't need in your client's tool picker (e.g. VS Code Chat panel) to keep the agent focused and responsive.

Roadmap

Version	Feature	Status
v0.4	HTTP transport + attribute management + schema consistency	✅ Released
v0.5	Enterprise auth (Client Credentials, Managed Identity, Entra JWT)	✅ Released
v0.6	MCP Prompts (5 templates) + MCP Resources (4)	✅ Released
v0.7	Schema write (create table/relationship) + Record Access (share, merge)	✅ Released (v0.7.5)

→ Full Roadmap

License

Related MCP servers

Python

View repository →

io.github.codex-curator/studiomcphub

Maintained

32 creative AI tools (18 free) for agents: generate, upscale, mockup, print, watermark.

Python

MIT

View repository →

WinBridgeAgent

Maintained

Open-source Windows MCP server for AI assistants with file, clipboard, screenshot, process, and power management.

C++

GPL-3.0

View repository →

MCP Dataverse MCP Server

What is the MCP Dataverse MCP server?

How to install MCP Dataverse

Tools & capabilities

Use cases

MCP Dataverse MCP server FAQ

MCP Dataverse

Why MCP Dataverse?

Install

Update

Authentication

Capabilities

HTTP Transport

Troubleshooting

Performance Tip

Roadmap

License

Related MCP servers

io.github.codevanmoose/truncus-mcp-server

io.github.codevanmoose/vanmoose-mcp-server

IssueFoundry Agent Market

Intelligence Aeternum

io.github.codex-curator/studiomcphub

WinBridgeAgent