79 tools · Production ready

The complete MCP server for
Microsoft Dataverse

Connect any AI client to Dataverse in minutes — query data, manage records, inspect schema, automate workflows. Three auth modes, zero lock-in.

Get started →All 79 tools GitHub ↗

$npx mcp-dataverse install

Tools

Resources

Prompts

Auth modes

See it in action

Pick a scenario — your AI agent calls the right tool and gets a structured response.

Tool Calldataverse_query

{
  "tool": "dataverse_query",
  "parameters": {
    "entityLogicalName": "account",
    "select": [
      "name",
      "revenue",
      "createdon"
    ],
    "filter": "revenue gt 1000000",
    "orderby": "revenue desc",
    "top": 5
  }
}

Response✓ 200 OK

{
  "summary": "5 accounts found (revenue > $1M)",
  "data": [
    {
      "name": "Contoso Ltd",
      "revenue": 8500000,
      "createdon": "2024-01-15"
    },
    {
      "name": "Fabrikam Inc",
      "revenue": 5200000,
      "createdon": "2023-11-02"
    },
    // ... 3 more records
  ],
  "suggestions": [
    "Use dataverse_get to fetch full details",
    "Try dataverse_execute_fetchxml for complex joins"
  ]
}

Capabilities

What your AI can do now

Six developer workflows, zero portal tabs. From schema exploration to bulk migrations — fully conversational.

Schema

Explore your entire data model

Map tables, relationships, option sets and entity keys across any Dataverse org — without opening the portal or reading a single doc.

Ask your AI"Which tables are related to Contact, and what are their primary keys?"

list_tablesget_table_metadataget_relationshipsget_option_set

Data

Query data in plain language

OData filter, FetchXML aggregate, full-text search, paginated retrieval — your AI writes the right query, runs it, and explains the results.

Ask your AI"Find all active Accounts in France modified this week, sorted by revenue"

queryexecute_fetchxmlsearchretrieve_multiple_with_paging

Operations

Migrate and update at scale

Up to 1,000 create, update or delete operations in one atomic batch. Build data migration scripts at the speed of a conversation.

Ask your AI"Archive all Leads from the 2022 campaign and reassign their open Tasks"

batch_executecreateupdateupsertassign

Security

Audit security in one conversation

List roles, inspect privilege sets, detect over-permissioned users, grant or revoke record access — your full RBAC model at a glance.

Ask your AI"Who has System Administrator role? Flag any non-admins with delete privileges on Contact"

list_rolesget_role_privilegesassign_role_to_usercheck_record_access

Observability

Debug plugins and flows — no portal

Pull trace logs and workflow execution history, then let AI diagnose the error, explain the call stack, and suggest the fix.

Ask your AI"Why did the Contact update plugin fail this morning? Show me the trace and suggest a fix"

get_plugin_trace_logsget_workflow_trace_logslist_plugin_stepslist_workflows

Customization

Extend schema, deploy, iterate

Create tables, add columns, configure lookups and relationships, set environment variables, publish customizations — all via chat.

Ask your AI"Add a Priority Score decimal column to Account, then publish the customization"

create_tablecreate_attributecreate_relationshipset_environment_variablepublish_customizations

Works with your favourite AI client

🤖VS Code Copilot🎭Claude Desktop🖱️Cursor🌊Windsurf💎Gemini CLI🧩Copilot Studio💻Codex CLI

Why MCP Dataverse

Built for production agents

Schema-aware, batch-capable, and battle-tested with the major MCP clients.

79 production-ready tools

Complete coverage — CRUD, metadata, FetchXML, batch, solutions, audit, RBAC. One server, every operation your AI needs.

Three auth modes

Interactive device code for local dev, service principal for CI/CD, managed identity for Azure-hosted deployments.

Zero-config quick start

One command runs an interactive wizard — fully configured in under 2 minutes. Just needs Node.js 20+.

Schema intelligence

AI agents see real schema — entity definitions, relationships, option sets. No hallucinated columns, no broken OData.

Batch & bulk operations

Up to 1 000 operations in a single atomic request. Built for migrations and bulk updates with full error reporting.

Works everywhere

VS Code Copilot, Claude Desktop, Cursor, Windsurf, Gemini CLI, Copilot Studio, Codex CLI — any MCP-compliant client.

Ready to connect your AI to Dataverse?

Install in under two minutes. Works with any MCP-compatible client.

Get started →Browse all capabilities