How does authentication work with Dynamics 365?

Dynamics 365 uses OAuth 2.0 via Microsoft Entra ID (Azure AD). You register an app in Azure Portal, obtain a Client ID and Client Secret, configure API permissions for Dynamics CRM, and create an Application User in your Dynamics environment.

Can I query custom entities and tables in Dataverse?

Yes. The `query_dataverse` tool queries any entity in Dataverse — standard or custom. Use OData filter expressions, $expand for related entities, and $select for specific columns.

Does it work with both Dynamics 365 Sales and Business Central?

Yes. The MCP server supports the Dataverse Web API (for Sales, Service, Marketing) and the Business Central API (for financials, inventory, purchasing). Just point to the correct environment URL.

Can I advance opportunities through pipeline stages?

Absolutely. The `update_record` tool can update the stage, probability, estimated revenue, and close date of any opportunity. The agent also supports advancing records through Business Process Flows.

Microsoft Dynamics 365 MCP Server for Pydantic AI 10 tools — connect in under 2 minutes

Name: Microsoft Dynamics 365
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 10 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Microsoft Dynamics 365 through the Vinkius and every tool is automatically validated against Pydantic schemas — catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Microsoft Dynamics 365 "
            "(10 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Microsoft Dynamics 365?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Microsoft Dynamics 365 MCP Server

Connect your Microsoft Dynamics 365 environment to any AI agent and manage your CRM and ERP operations through natural conversation.

Pydantic AI validates every Microsoft Dynamics 365 tool response against typed schemas, catching data inconsistencies at build time. Connect 10 tools through the Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code — full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Account Management — Create, read, and update account records including contacts, addresses, and relationship hierarchies
Opportunity Pipeline — Query open opportunities by stage, probability, and close date; update deal values and ownership
Sales Orders — Create and manage sales orders, quotes, and invoices across your sales organization
Case Management — Create support cases, track resolution progress, and manage SLA compliance
Financial Operations — Query journal entries, G/L accounts, and financial dimensions (Business Central)
Custom Entities — Access any Dataverse entity through the Web API, including custom tables and relationships
Business Process Flows — Check active stages in business process flows and advance records through pipeline stages

The Microsoft Dynamics 365 MCP Server exposes 10 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Microsoft Dynamics 365 to Pydantic AI via MCP

Follow these steps to integrate the Microsoft Dynamics 365 MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 10 tools from Microsoft Dynamics 365 with type-safe schemas

Why Use Pydantic AI with the Microsoft Dynamics 365 MCP Server

Pydantic AI provides unique advantages when paired with Microsoft Dynamics 365 through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture — switch between OpenAI, Anthropic, or Gemini without changing your Microsoft Dynamics 365 integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Microsoft Dynamics 365 connection logic from agent behavior for testable, maintainable code

Microsoft Dynamics 365 + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Microsoft Dynamics 365 MCP Server delivers measurable value.

Type-safe data pipelines: query Microsoft Dynamics 365 with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Microsoft Dynamics 365 tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Microsoft Dynamics 365 and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Microsoft Dynamics 365 responses and write comprehensive agent tests

Microsoft Dynamics 365 MCP Tools for Pydantic AI (10)

These 10 tools become available when you connect Microsoft Dynamics 365 to Pydantic AI via MCP:

count_records

Useful for dashboards without fetching full records. Count records in a Dynamics 365 entity set

create_record

Provide field values as JSON. For lookups, use the @odata.bind format. Create a new record in Dynamics 365

delete_record

This action is irreversible. Delete a Dynamics 365 record

get_record

Example: get_record("accounts", "00000000-0000-0000-0000-000000000001"). Get a specific Dynamics 365 record

list_accounts

Use filter to narrow results. List Dynamics 365 accounts

list_cases

List support cases (incidents)

list_contacts

List Dynamics 365 contacts

list_opportunities

Filter by stage, close date, or estimated value. List sales opportunities

query_dataverse

Common entity sets: accounts, contacts, opportunities, incidents (cases), leads, salesorders, invoices. Use OData filter syntax. Query any Dataverse entity set

update_record

Only specify the fields you want to change. Update an existing Dynamics 365 record

Example Prompts for Microsoft Dynamics 365 in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Microsoft Dynamics 365 immediately.

"Show me all opportunities closing this month with value above $100K."

"Create a new support case for account 'Contoso Ltd' about a billing discrepancy."

"What's the total revenue from the EMEA region this quarter?"

Troubleshooting Microsoft Dynamics 365 MCP Server with Pydantic AI

Common issues when connecting Microsoft Dynamics 365 to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Microsoft Dynamics 365 + Pydantic AI FAQ

Common questions about integrating Microsoft Dynamics 365 MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer — your Microsoft Dynamics 365 MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.